skills/iliaal/ai-skills/compound-docs/Gen Agent Trust Hub

compound-docs

Pass

Audited by Gen Agent Trust Hub on Sep 20, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill relies on the PyYAML Python package for frontmatter validation. Instructions in SKILL.md and scripts/validate-frontmatter.py advise the user to install this dependency using standard package management tools.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes data from user conversation history to generate documentation, representing an indirect prompt injection surface.
  • Ingestion points: Data is extracted from conversation history as described in Step 2 of references/documentation-process.md to populate documentation fields.
  • Boundary markers: Explicit delimiters or instructions to ignore embedded commands are absent in the documentation generation templates.
  • Capability inventory: The skill performs directory creation, writes markdown files to the local file system (docs/solutions/), and executes a local Python validation script (scripts/validate-frontmatter.py).
  • Sanitization: The skill incorporates filename sanitization (Step 4) and a mandatory YAML schema validation gate (Step 5) to verify the integrity of the generated metadata before final documentation is created.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 20, 2026, 08:34 AM
Security Audit — agent-trust-hub — compound-docs