Trust Assessment
claude-code-mastery received a trust score of 10/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 49 findings: 23 critical, 12 high, 14 medium, and 0 low severity. Key findings include Persistence / self-modification instructions, Arbitrary command execution, File read + network send exfiltration.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Manifest Analysis layer scored lowest at 0/100, indicating areas for improvement.
Last analyzed on February 14, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings49
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Persistence / self-modification instructions Shell RC file modification for persistence Remove any persistence mechanisms. Skills should not modify system startup configurations, crontabs, LaunchAgents, systemd services, or shell profiles. | Manifest | skills/cheenu1092-oss/claude-code-mastery/scripts/02-install-claude-code.sh:47 | |
| CRITICAL | Persistence / self-modification instructions Shell RC file modification for persistence Remove any persistence mechanisms. Skills should not modify system startup configurations, crontabs, LaunchAgents, systemd services, or shell profiles. | Manifest | skills/cheenu1092-oss/claude-code-mastery/scripts/02-install-claude-code.sh:50 | |
| CRITICAL | Persistence / self-modification instructions Shell RC file modification for persistence Remove any persistence mechanisms. Skills should not modify system startup configurations, crontabs, LaunchAgents, systemd services, or shell profiles. | Manifest | skills/cheenu1092-oss/claude-code-mastery/scripts/02-install-claude-code.sh:53 | |
| CRITICAL | Persistence / self-modification instructions Shell RC file modification for persistence Remove any persistence mechanisms. Skills should not modify system startup configurations, crontabs, LaunchAgents, systemd services, or shell profiles. | Manifest | skills/cheenu1092-oss/claude-code-mastery/scripts/08-troubleshoot.sh:87 | |
| CRITICAL | Arbitrary command execution Remote code download piped to interpreter Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands. | Manifest | skills/cheenu1092-oss/claude-code-mastery/scripts/01-check-dependencies.sh:46 | |
| CRITICAL | Arbitrary command execution Remote code download piped to interpreter Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands. | Manifest | skills/cheenu1092-oss/claude-code-mastery/scripts/02-install-claude-code.sh:27 | |
| CRITICAL | Arbitrary command execution Remote code download piped to interpreter Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands. | Manifest | skills/cheenu1092-oss/claude-code-mastery/scripts/05-setup-claude-mem.sh:124 | |
| CRITICAL | File read + network send exfiltration AI agent config/credential file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality. | Manifest | skills/cheenu1092-oss/claude-code-mastery/scripts/04-install-subagents.sh:3 | |
| CRITICAL | File read + network send exfiltration AI agent config/credential file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality. | Manifest | skills/cheenu1092-oss/claude-code-mastery/scripts/06-diagnostics.sh:87 | |
| CRITICAL | File read + network send exfiltration AI agent config/credential file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality. | Manifest | skills/cheenu1092-oss/claude-code-mastery/scripts/07-weekly-improvement-cron.sh:145 | |
| CRITICAL | File read + network send exfiltration AI agent config/credential file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality. | Manifest | skills/cheenu1092-oss/claude-code-mastery/scripts/07-weekly-improvement-cron.sh:151 | |
| CRITICAL | File read + network send exfiltration AI agent config/credential file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality. | Manifest | skills/cheenu1092-oss/claude-code-mastery/scripts/07-weekly-improvement-cron.sh:157 | |
| CRITICAL | File read + network send exfiltration AI agent config/credential file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality. | Manifest | skills/cheenu1092-oss/claude-code-mastery/scripts/uninstall.sh:38 | |
| CRITICAL | File read + network send exfiltration AI agent config/credential file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality. | Manifest | skills/cheenu1092-oss/claude-code-mastery/scripts/uninstall.sh:39 | |
| CRITICAL | File read + network send exfiltration AI agent config/credential file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality. | Manifest | skills/cheenu1092-oss/claude-code-mastery/scripts/uninstall.sh:54 | |
| CRITICAL | File read + network send exfiltration AI agent config/credential file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality. | Manifest | skills/cheenu1092-oss/claude-code-mastery/scripts/uninstall.sh:55 | |
| CRITICAL | File read + network send exfiltration AI agent config/credential file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality. | Manifest | skills/cheenu1092-oss/claude-code-mastery/scripts/uninstall.sh:163 | |
| CRITICAL | File read + network send exfiltration AI agent config/credential file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality. | Manifest | skills/cheenu1092-oss/claude-code-mastery/scripts/uninstall.sh:164 | |
| CRITICAL | Remote code execution: curl/wget pipe to shell Detected a pattern that downloads and immediately executes remote code. This is a primary malware delivery vector. Never pipe curl/wget output directly to a shell interpreter. | Static | skills/cheenu1092-oss/claude-code-mastery/scripts/01-check-dependencies.sh:46 | |
| CRITICAL | Remote code execution: curl/wget pipe to shell Detected a pattern that downloads and immediately executes remote code. This is a primary malware delivery vector. Never pipe curl/wget output directly to a shell interpreter. | Static | skills/cheenu1092-oss/claude-code-mastery/scripts/02-install-claude-code.sh:27 | |
| CRITICAL | Remote code execution: curl/wget pipe to shell Detected a pattern that downloads and immediately executes remote code. This is a primary malware delivery vector. Never pipe curl/wget output directly to a shell interpreter. | Static | skills/cheenu1092-oss/claude-code-mastery/scripts/05-setup-claude-mem.sh:124 | |
| CRITICAL | Unsafe Remote Script Execution (curl | sh) for Claude Code The installation script for Claude Code uses `curl -fsSL <URL> | sh`. This practice executes arbitrary code downloaded from a remote server without prior inspection. If the remote server (`claude.ai`) were compromised, this could lead to arbitrary code execution on the user's system, bypassing security checks and potentially installing malicious software or exfiltrating data. Avoid piping `curl` output directly to `sh`. Instead, download the script, review its contents, and then execute it. For example: ```bash curl -fsSL -o install-claude.sh https://claude.ai/install.sh # Review install-claude.sh bash install-claude.sh ``` | LLM | scripts/02-install-claude-code.sh:20 | |
| CRITICAL | Unsafe Remote Script Execution (curl | sh) for Bun The `claude-mem` setup script suggests installing Bun using `curl -fsSL https://bun.sh/install | bash`. Similar to the Claude Code installation, this executes arbitrary code downloaded from a remote server without prior inspection. A compromise of `bun.sh` could lead to arbitrary code execution on the user's system. Avoid piping `curl` output directly to `sh`. Instead, download the script, review its contents, and then execute it. For example: ```bash curl -fsSL -o install-bun.sh https://bun.sh/install # Review install-bun.sh bash install-bun.sh ``` | LLM | scripts/05-setup-claude-mem.sh:100 | |
| HIGH | Sensitive path access: AI agent config Access to AI agent config path detected: '~/.claude/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | skills/cheenu1092-oss/claude-code-mastery/scripts/04-install-subagents.sh:3 | |
| HIGH | Sensitive path access: AI agent config Access to AI agent config path detected: '~/.claude/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | skills/cheenu1092-oss/claude-code-mastery/scripts/06-diagnostics.sh:87 | |
| HIGH | Sensitive path access: AI agent config Access to AI agent config path detected: '~/.claude/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | skills/cheenu1092-oss/claude-code-mastery/scripts/07-weekly-improvement-cron.sh:145 | |
| HIGH | Sensitive path access: AI agent config Access to AI agent config path detected: '~/.claude/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | skills/cheenu1092-oss/claude-code-mastery/scripts/07-weekly-improvement-cron.sh:151 | |
| HIGH | Sensitive path access: AI agent config Access to AI agent config path detected: '~/.claude/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | skills/cheenu1092-oss/claude-code-mastery/scripts/07-weekly-improvement-cron.sh:157 | |
| HIGH | Sensitive path access: AI agent config Access to AI agent config path detected: '~/.claude/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | skills/cheenu1092-oss/claude-code-mastery/scripts/uninstall.sh:38 | |
| HIGH | Sensitive path access: AI agent config Access to AI agent config path detected: '~/.claude/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | skills/cheenu1092-oss/claude-code-mastery/scripts/uninstall.sh:39 | |
| HIGH | Sensitive path access: AI agent config Access to AI agent config path detected: '~/.claude/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | skills/cheenu1092-oss/claude-code-mastery/scripts/uninstall.sh:54 | |
| HIGH | Sensitive path access: AI agent config Access to AI agent config path detected: '~/.claude/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | skills/cheenu1092-oss/claude-code-mastery/scripts/uninstall.sh:55 | |
| HIGH | Sensitive path access: AI agent config Access to AI agent config path detected: '~/.claude/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | skills/cheenu1092-oss/claude-code-mastery/scripts/uninstall.sh:163 | |
| HIGH | Sensitive path access: AI agent config Access to AI agent config path detected: '~/.claude/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | skills/cheenu1092-oss/claude-code-mastery/scripts/uninstall.sh:164 | |
| HIGH | Supply Chain Risk: Unpinned Git Branch Fallback The `claude-mem` installation script attempts to clone a Git repository and checkout a specific, pinned commit (`CLAUDE_MEM_COMMIT`). However, if checking out this pinned commit fails, the script falls back to checking out the `main` branch. This fallback negates the security benefit of pinning, as the `main` branch is unpinned and its contents can change at any time, potentially introducing malicious code if the upstream repository (`thedotmack/claude-mem`) is compromised. Remove the fallback to `git checkout main`. If the pinned commit cannot be checked out, the installation should fail, prompting the user to investigate or update the pinned commit hash. This ensures that only reviewed and trusted code is installed. | LLM | scripts/05-setup-claude-mem.sh:127 | |
| MEDIUM | Sensitive environment variable access: $HOME Access to sensitive environment variable '$HOME' detected in shell context. Verify this environment variable access is necessary and the value is not exfiltrated. | Static | skills/cheenu1092-oss/claude-code-mastery/config.sh:80 | |
| MEDIUM | Sensitive environment variable access: $HOME Access to sensitive environment variable '$HOME' detected in shell context. Verify this environment variable access is necessary and the value is not exfiltrated. | Static | skills/cheenu1092-oss/claude-code-mastery/scripts/01-check-dependencies.sh:84 | |
| MEDIUM | Sensitive environment variable access: $HOME Access to sensitive environment variable '$HOME' detected in shell context. Verify this environment variable access is necessary and the value is not exfiltrated. | Static | skills/cheenu1092-oss/claude-code-mastery/scripts/02-install-claude-code.sh:44 | |
| MEDIUM | Persistence mechanism: Shell RC file modification Detected Shell RC file modification pattern. Persistence mechanisms allow malware to survive system restarts. Review this persistence pattern. Skills should not modify system startup configuration. | Static | skills/cheenu1092-oss/claude-code-mastery/scripts/02-install-claude-code.sh:47 | |
| MEDIUM | Persistence mechanism: Shell RC file modification Detected Shell RC file modification pattern. Persistence mechanisms allow malware to survive system restarts. Review this persistence pattern. Skills should not modify system startup configuration. | Static | skills/cheenu1092-oss/claude-code-mastery/scripts/02-install-claude-code.sh:50 | |
| MEDIUM | Persistence mechanism: Shell RC file modification Detected Shell RC file modification pattern. Persistence mechanisms allow malware to survive system restarts. Review this persistence pattern. Skills should not modify system startup configuration. | Static | skills/cheenu1092-oss/claude-code-mastery/scripts/02-install-claude-code.sh:53 | |
| MEDIUM | Sensitive environment variable access: $HOME Access to sensitive environment variable '$HOME' detected in shell context. Verify this environment variable access is necessary and the value is not exfiltrated. | Static | skills/cheenu1092-oss/claude-code-mastery/scripts/03-first-time-auth.sh:7 | |
| MEDIUM | Sensitive environment variable access: $HOME Access to sensitive environment variable '$HOME' detected in shell context. Verify this environment variable access is necessary and the value is not exfiltrated. | Static | skills/cheenu1092-oss/claude-code-mastery/scripts/04-install-subagents.sh:88 | |
| MEDIUM | Sensitive environment variable access: $HOME Access to sensitive environment variable '$HOME' detected in shell context. Verify this environment variable access is necessary and the value is not exfiltrated. | Static | skills/cheenu1092-oss/claude-code-mastery/scripts/05-setup-claude-mem.sh:71 | |
| MEDIUM | Sensitive environment variable access: $USER Access to sensitive environment variable '$USER' detected in shell context. Verify this environment variable access is necessary and the value is not exfiltrated. | Static | skills/cheenu1092-oss/claude-code-mastery/scripts/06-diagnostics.sh:48 | |
| MEDIUM | Sensitive environment variable access: $HOME Access to sensitive environment variable '$HOME' detected in shell context. Verify this environment variable access is necessary and the value is not exfiltrated. | Static | skills/cheenu1092-oss/claude-code-mastery/scripts/06-diagnostics.sh:49 | |
| MEDIUM | Sensitive environment variable access: $HOME Access to sensitive environment variable '$HOME' detected in shell context. Verify this environment variable access is necessary and the value is not exfiltrated. | Static | skills/cheenu1092-oss/claude-code-mastery/scripts/08-troubleshoot.sh:76 | |
| MEDIUM | Persistence mechanism: Shell RC file modification Detected Shell RC file modification pattern. Persistence mechanisms allow malware to survive system restarts. Review this persistence pattern. Skills should not modify system startup configuration. | Static | skills/cheenu1092-oss/claude-code-mastery/scripts/08-troubleshoot.sh:87 | |
| MEDIUM | Sensitive environment variable access: $HOME Access to sensitive environment variable '$HOME' detected in shell context. Verify this environment variable access is necessary and the value is not exfiltrated. | Static | skills/cheenu1092-oss/claude-code-mastery/scripts/uninstall.sh:74 |
Scan History
Embed Code
[](https://skillshield.io/report/e155d0d07a4eaf87)
Powered by SkillShield