Trust Assessment
production-readiness received a trust score of 94/100, placing it in the Trusted category. This skill has passed all critical security checks and demonstrates strong security practices.
SkillShield's automated analysis identified 1 finding: 0 critical, 0 high, 1 medium, and 0 low severity. Key findings include Skill delegates execution to unverified sub-skills.
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 | |
|---|---|---|---|---|
| MEDIUM | Skill delegates execution to unverified sub-skills This meta-skill explicitly instructs the LLM to 'Read the target skill first, follow its instructions, then return results here for synthesis.' This design pattern means the security of this skill is entirely dependent on the security and trustworthiness of all referenced sub-skills and agents (e.g., 'logging-observability', 'security-review', 'docker-expert', '/generate-docs'). A compromise or malicious instruction within any of these delegated skills could be executed via this meta-skill, leading to prompt injection, data exfiltration, or command injection. Implement strict vetting and sandboxing for all referenced sub-skills. Ensure that delegated skills operate with the principle of least privilege. Consider explicit version pinning for referenced skills if the ecosystem supports it, to prevent unexpected changes. | LLM | SKILL.md:97 |
Scan History
Embed Code
[](https://skillshield.io/report/b0170b2029d4f3b8)
Powered by SkillShield