doc-maintenance

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes shell commands for git (log, checkout, add, commit, push) and the GitHub CLI (gh pr create) to automate the documentation maintenance workflow. These actions are appropriately scoped to the skill's purpose of managing repository documentation.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from git commit messages and markdown files to identify shipped features and breaking changes. Ingestion points: Auditing of README.md, doc/SPEC.md, and doc/PRODUCT.md, as well as parsing git log output. Boundary markers: The skill lacks explicit delimiters or instructions to ignore potential injections within the audited content. Capability inventory: File system writes, branch management, and remote repository interaction (push/PR) via git and gh. Sanitization: No specific sanitization logic is applied to the ingested text before it is used to generate PR descriptions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 07:35 AM
Security Audit — agent-trust-hub — doc-maintenance