Security Audit
caam
github.com/Mrc220/agent_flywheel_clawdbot_skills_and_integrationsTrust Assessment
caam 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 12 findings: 7 critical, 2 high, 3 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 June 1, 2026 (commit 6a655802). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings12
| 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/caam/SKILL.md:447 | |
| 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/caam/SKILL.md:55 | |
| 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/caam/SKILL.md:465 | |
| CRITICAL | File read + network send exfiltration Package manager / git 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/caam/SKILL.md:369 | |
| 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/caam/SKILL.md:105 | |
| 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/caam/SKILL.md:55 | |
| 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/caam/SKILL.md:465 | |
| 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/caam/SKILL.md:105 | |
| HIGH | Unsafe `curl | bash` installation method The recommended installation method for the `caam` tool involves piping a script fetched from a remote URL directly to `bash`. This allows arbitrary code execution from an external source, posing a significant supply chain risk if the remote repository is compromised or the script is malicious. The use of a cache-buster `?$(date +%s)` ensures the latest version is always fetched, which exacerbates the risk by preventing users from relying on a previously verified version. Avoid `curl | bash` for installation. Instead, recommend installing from a trusted package manager, a signed binary, or by requiring users to manually review the script before execution. If `curl | bash` is deemed absolutely necessary, pin the script to a specific version or commit hash to prevent unexpected changes. | Static | SKILL.md:140 | |
| 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/caam/SKILL.md:97 | |
| 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/caam/SKILL.md:447 | |
| MEDIUM | Unpinned `go install` dependency The `go install` command uses `@latest` to fetch the `caam` tool. This means the tool will be installed from the most recent version available, which introduces a supply chain risk. A future malicious or vulnerable version could be published and installed without explicit user consent or review of the specific version. Pin the dependency to a specific version or commit hash (e.g., `@v1.2.3` or `@<commit_hash>`) to ensure reproducible and secure builds. This allows users to explicitly verify the version they are installing. | Static | SKILL.md:147 |
Scan History
Embed Code
[](https://skillshield.io/report/a7c2c298b36b0ced)
Powered by SkillShield