Security Audit
strategic-compact
github.com/affaan-m/everything-claude-codeTrust Assessment
strategic-compact 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, Skill instructs user to configure arbitrary code execution via `command` 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 | .agents/skills/strategic-compact/SKILL.md:36 | |
| 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 | .agents/skills/strategic-compact/SKILL.md:44 | |
| 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 | .agents/skills/strategic-compact/SKILL.md:48 | |
| 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 | .agents/skills/strategic-compact/SKILL.md:81 | |
| 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 | .agents/skills/strategic-compact/SKILL.md:36 | |
| 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 | .agents/skills/strategic-compact/SKILL.md:44 | |
| 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 | .agents/skills/strategic-compact/SKILL.md:48 | |
| 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 | .agents/skills/strategic-compact/SKILL.md:81 | |
| HIGH | Skill instructs user to configure arbitrary code execution via `command` hook The `SKILL.md` documentation instructs users to add a `PreToolUse` hook that executes an external Node.js script: `node ~/.claude/skills/strategic-compact/suggest-compact.js`. This mechanism allows the skill to execute arbitrary code on the user's system with the privileges of the user running Claude. While the content of `suggest-compact.js` is not provided for analysis, the ability to execute arbitrary code via a hook poses a significant security risk if the script contains malicious logic, vulnerabilities, or performs unintended actions. Review the source code of `suggest-compact.js` thoroughly for any malicious or vulnerable patterns. If the script's functionality can be achieved through safer, sandboxed methods (e.g., built-in Claude features, less privileged APIs), those should be preferred. Users should be explicitly warned about the implications of running arbitrary code from third-party skills and advised to review the script's source code before installation. | LLM | SKILL.md:39 |
Scan History
Embed Code
[](https://skillshield.io/report/3477c1d81a234e5f)
Powered by SkillShield