chapter-outline-generator
Pass
Audited by Gen Agent Trust Hub on Jul 9, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill provides structured instructions for generating text-based book outlines. It does not perform any sensitive operations, file access, or network calls. The findings in the provided 'skill-report.json' regarding external commands are false positives triggered by standard Markdown code blocks used for formatting examples.
- [NO_CODE]: No scripts or executable files are included with the skill. All functionality is handled through natural language prompts.
- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it ingests untrusted user data (book details) in Step 1 of SKILL.md. Evidence Chain: 1. Ingestion points: Step 1 collects title, genre, and theme. 2. Boundary markers: None present. 3. Capability inventory: No capabilities detected (no shell, file, or network tools). 4. Sanitization: None present. Due to the complete absence of exploitable capabilities, this surface poses no security risk.
Audit Metadata