Trust Assessment
clawdbot-self-security-audit received a trust score of 70/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 1 finding: 1 critical, 0 high, 0 medium, and 0 low severity. Key findings include Skill performs write operations despite claiming to be read-only.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. All layers scored 70 or above, reflecting consistent security practices.
Last analyzed on February 13, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Skill performs write operations despite claiming to be read-only The skill's manifest (trusted input) declares `SKILL.md` as an executable binary (`bins: ["SKILL.md"]`) and requires `exec` and `bash` tools. The `SKILL.md` file, which is treated as executable content, contains `bash` code blocks under "Remediation" sections (e.g., `chmod 700 ~/.clawdbot`, `chmod 600 ~/.clawdbot/credentials/*`) and explicitly states that the `--fix` flag "applies these guardrails" including tightening local permissions. These actions involve modifying filesystem permissions, directly contradicting the skill's description as a "read-only security audit" in the manifest and the `readOnly: true`, `modifiesSettings: false`, `fileSystemAccess: ["read"]` declarations in the `skill.json` (untrusted self-declaration). Executing these commands could lead to unintended system modifications, privilege escalation, or data loss if misused. Reconcile the skill's functionality with its declared permissions. If write operations (like `chmod`) are intended, the skill must explicitly declare `modifiesSettings: true` and `fileSystemAccess: ["read", "write"]` in its manifest and `skill.json`. If the skill is truly meant to be read-only, all write-performing commands must be removed from `SKILL.md` and the `security-check.js` implementation. Remediation actions should be presented as recommendations for the user to execute manually, or be implemented in a separate, clearly marked "fix" skill with appropriate permissions. | LLM | SKILL.md:99 |
Scan History
Embed Code
[](https://skillshield.io/report/51b6b4bfe7a4b4dd)
Powered by SkillShield