Security Audit
frankxai/claude-skills-library:absorbed/harness/security-review
github.com/frankxai/claude-skills-libraryTrust Assessment
frankxai/claude-skills-library:absorbed/harness/security-review received a trust score of 85/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Fail-Open Security Policy for Markdown Files.
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 October 20, 2026 (commit 93c4aad5). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Fail-Open Security Policy for Markdown Files The skill instructions explicitly mandate a 'fail-open' policy for markdown warnings ('A markdown warning must exit 0'). Since markdown files are a common vector for prompt injection and malicious instructions in LLM agent environments, forcing security warnings on markdown files to exit with a success code (0) allows potentially malicious content to bypass security reviews undetected. Remove the requirement to force markdown warnings to exit 0. Ensure all security warnings, regardless of file type, are treated as blocking or require explicit user approval before proceeding. | LLM | SKILL.md:23 |
Scan History
Embed Code
[](https://skillshield.io/report/914f0a10f98ccb44)
Powered by SkillShield