git-pr-workflows-pr-enhance

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The script in resources/implementation-playbook.md uses subprocess.run to execute git diff commands on the local system. This allows the agent to interact with the host's version control system to extract repository data.
  • [PROMPT_INJECTION]: The skill exhibits an Indirect Prompt Injection surface (Category 8) by processing unvetted content from git diffs and commit messages.
  • Ingestion points: Data enters the agent context through analyze_changes and generate_pr_description in resources/implementation-playbook.md, which read diff outputs and commit history.
  • Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat data from the repository as untrusted or to ignore instructions embedded within code comments or commit logs.
  • Capability inventory: The skill possesses capabilities for local command execution (git) and structured text generation based on the inputs.
  • Sanitization: No validation or sanitization is performed on the ingested repository data before it is interpreted or used to generate outputs.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 12:04 PM