pull-request

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes shell commands to automate the pull request workflow. This includes running git push, gh pr create, and a local helper script node scripts/detect-issue.js to manage repository state and GitHub interactions.
  • [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection by incorporating external, potentially untrusted data into the agent's context.
  • Ingestion points: The SKILL.md file uses dynamic context injection to read the output of git log and git diff directly into the prompt.
  • Boundary markers: Absent. The skill does not use specific delimiters or instructions to isolate the Git output from the agent's core instructions.
  • Capability inventory: The skill provides the agent with the ability to push code changes and create pull requests, which could be exploited if malicious instructions in a commit message were followed.
  • Sanitization: Absent. No validation or filtering is performed on the data retrieved from the local Git repository before it is presented to the model.
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 09:43 AM
Security Audit — agent-trust-hub — pull-request