skills/asterixcapri/skills/to-docs/Gen Agent Trust Hub

to-docs

Pass

Audited by Gen Agent Trust Hub on Aug 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill identifies a dependency on an external repository and suggests a manual installation command to the user.
  • Source: Reference to mattpocock/skills on GitHub.
  • Method: Recommends the execution of npx skills@latest add mattpocock/skills --skill writing-for-agents if the dependency is missing.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the repository and user-provided work which could contain malicious instructions.
  • Ingestion points: Reads repository instructions, existing documentation files, conversation history, and code diffs (SKILL.md, Phase 1 steps 1 and 2).
  • Boundary markers: There are no instructions to use specific delimiters or protective wrappers when the agent reads external file content.
  • Capability inventory: The skill has the authority to edit project documentation and modify enforcement configurations, including lint rules and tests (SKILL.md, Phase 2 steps 4 and 5).
  • Sanitization: The instructions do not define sanitization, validation, or filtering logic for content extracted from the repository before it is processed.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 16, 2026, 05:47 PM
Security Audit — agent-trust-hub — to-docs