review-self

Pass

Audited by Gen Agent Trust Hub on May 19, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes various git and gh (GitHub CLI) commands to manage the repository workflow. This includes git status, git log, git diff, git push, and gh pr create. These operations are consistent with the skill's primary purpose of PR management.
  • [DATA_EXFILTRATION]: The skill accesses local repository data, including code diffs and metadata (remotes, branches). This information is used to generate PR descriptions and is only transmitted to the user's authorized GitHub repository during the PR creation process.
  • [PROMPT_INJECTION]: The skill ingests untrusted code from diffs to generate PR summaries, which presents a surface for indirect prompt injection. However, the risk is mitigated by the skill's structured approach, using domain-specific templates and instructions that guide the agent to perform objective analysis rather than following instructions embedded in the code.
Audit Metadata
Risk Level
SAFE
Analyzed
May 19, 2026, 02:36 PM
Security Audit — agent-trust-hub — review-self