babysit-pr

Pass

Audited by Gen Agent Trust Hub on Apr 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/gh_pr_watch.py invokes the gh CLI using subprocess.run with a list of strings for command and arguments. This is a secure implementation that avoids shell injection vulnerabilities.- [PROMPT_INJECTION]: The skill is susceptible to Indirect Prompt Injection (Category 8) because it fetches and processes external data from GitHub PR comments and reviews to drive automated code edits. A malicious contributor could embed instructions in a comment to influence the agent's behavior.
  • Ingestion points: GitHub issue comments and PR review comments are fetched via gh api in scripts/gh_pr_watch.py.
  • Boundary markers: The data is processed as structured JSON, but the prompt instructions lack explicit delimiters or warnings for the agent to ignore instructions embedded within the fetched text.
  • Capability inventory: The agent has the capability to edit files, commit changes, push to remote branches, and execute local scripts.
  • Sanitization: The script performs an author association check (restricting input to OWNER, MEMBER, and COLLABORATOR), but does not sanitize or filter the content of the comments themselves.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 1, 2026, 10:01 PM
Security Audit — agent-trust-hub — babysit-pr