mkdocs-documentation
Pass
Audited by Gen Agent Trust Hub on Mar 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses standard MkDocs command-line tools for local site serving and build validation. Evidence: Instructions in SKILL.md and references/testing.md call for 'mkdocs serve' and 'mkdocs build --strict'.\n- [PROMPT_INJECTION]: The skill is instructed to prioritize project-specific documentation files which can override general behavior, representing an indirect prompt injection surface. Evidence: SKILL.md explicitly directs the agent to check 'docs/dev/ai/skills/' and 'docs/dev/ai/agents/' and states these files 'take precedence'. Ingestion points: 'docs/dev/ai/skills/' and 'docs/dev/ai/agents/'. Boundary markers: Absent. Capability inventory: Shell command execution via 'mkdocs'. Sanitization: Absent.
Audit Metadata