documentation-generation-doc-generate

Pass

Audited by Gen Agent Trust Hub on Jul 9, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it ingests untrusted code and comments to generate documentation.\n
  • Ingestion points: SKILL.md (extracts from code) and resources/implementation-playbook.md (parses files via ast).\n
  • Boundary markers: No explicit markers or instructions are provided to the agent to disregard embedded commands in the source data.\n
  • Capability inventory: The skill is capable of writing files and configuring automation workflows.\n
  • Sanitization: No sanitization is implemented for the content extracted from the codebase before processing.\n- [COMMAND_EXECUTION]: The skill facilitates the setup of automated documentation pipelines which involve shell command execution.\n
  • Evidence: resources/implementation-playbook.md includes templates for CI/CD workflows and instructions for documentation linting.\n- [EXTERNAL_DOWNLOADS]: The skill references and installs tools from well-known technology services.\n
  • Evidence: Uses cdn.jsdelivr.net for documentation assets and installs @redocly/cli via npm.\n
  • Context: These sources are well-known industry providers and consistent with standard development practices.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 9, 2026, 07:07 AM
Security Audit — agent-trust-hub — documentation-generation-doc-generate