pull-request-message

Pass

Audited by Gen Agent Trust Hub on May 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses local git commands to analyze the repository state.
  • Evidence: SKILL.md instructs the agent to run git status, git diff, and git log to gather context for the PR description.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting external data from the repository without using boundary markers.
  • Ingestion points: SKILL.md reads untrusted data from git diffs, commit logs, issue descriptions, and existing PR drafts.
  • Boundary markers: Absent. The instructions do not define clear delimiters to separate instructions from the ingested repository data.
  • Capability inventory: SKILL.md perform local command execution via git subprocesses.
  • Sanitization: Absent. There is no evidence of filtering or sanitizing the input data before it is incorporated into the prompt context.
Audit Metadata
Risk Level
SAFE
Analyzed
May 18, 2026, 05:52 AM
Security Audit — agent-trust-hub — pull-request-message