contribute-docs

Pass

Audited by Gen Agent Trust Hub on Jul 22, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill mentions the command just docs in its checklist for validating documentation site changes. just is a widely used, legitimate command-line utility for task automation in software development, and its use here is consistent with standard project maintenance workflows.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and modify documentation and example files (Markdown, MDX, and YAML). This creates a surface for indirect prompt injection where malicious instructions could be embedded in the data being edited. However, the skill mitigates this by enforcing specific structural rules and requiring alignment with documented public behaviors.
  • Ingestion points: Processes README.md, docs/index.yml, and MDX files.
  • Boundary markers: Not explicitly defined for prompt isolation, though formatting rules for comments are established.
  • Capability inventory: Involves file system modifications and execution of the just command runner.
  • Sanitization: No specific data sanitization or filtering logic is present in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 22, 2026, 08:01 AM
Security Audit — agent-trust-hub — contribute-docs