Security Audit
affaan-m/everything-claude-code:docs/ja-JP/skills/continuous-learning
github.com/affaan-m/everything-claude-codeTrust Assessment
affaan-m/everything-claude-code:docs/ja-JP/skills/continuous-learning received a trust score of 0/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 9 findings: 4 critical, 5 high, 0 medium, and 0 low severity. Key findings include File read + network send exfiltration, Sensitive path access: AI agent config, Direct Shell Script Execution via Hook.
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 March 20, 2026 (commit 9a478ad6). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings9
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| 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 | docs/ja-JP/skills/continuous-learning/SKILL.md:12 | |
| 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 | docs/ja-JP/skills/continuous-learning/SKILL.md:23 | |
| 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 | docs/ja-JP/skills/continuous-learning/SKILL.md:51 | |
| 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 | docs/ja-JP/skills/continuous-learning/SKILL.md:60 | |
| 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 | docs/ja-JP/skills/continuous-learning/SKILL.md:12 | |
| 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 | docs/ja-JP/skills/continuous-learning/SKILL.md:23 | |
| 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 | docs/ja-JP/skills/continuous-learning/SKILL.md:51 | |
| 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 | docs/ja-JP/skills/continuous-learning/SKILL.md:60 | |
| HIGH | Direct Shell Script Execution via Hook The skill is configured to execute a shell script (`evaluate-session.sh`) as a `Stop` hook for all sessions (`"matcher": "*"`). This direct execution of an arbitrary shell script, especially one that processes untrusted input (like Claude Code session content), presents a significant command injection risk. If the `evaluate-session.sh` script does not properly sanitize its inputs, a malicious actor could craft session content to inject and execute arbitrary commands on the host system with the privileges of the Claude Code process. Thoroughly audit the `evaluate-session.sh` script for command injection vulnerabilities. Ensure all external inputs, particularly session content, are strictly validated, sanitized, and properly escaped before being used in shell commands. Consider using a more secure execution environment (e.g., a sandboxed Python script) if complex parsing of untrusted input is required, and ensure the script runs with the principle of least privilege. | LLM | SKILL.md:63 |
Scan History
Embed Code
[](https://skillshield.io/report/044627ebc6d9e637)
Powered by SkillShield