iterate-pr

Pass

Audited by Gen Agent Trust Hub on Mar 31, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by fetching and acting on PR feedback and CI logs. An attacker could provide malicious instructions in a PR comment that the agent might execute while attempting to address feedback. 1. Ingestion points: The skill uses scripts/fetch_pr_feedback.py and scripts/fetch_pr_checks.py to pull data from GitHub. 2. Boundary markers: No markers are used to separate instructions from data. 3. Capability inventory: The agent has permissions to modify local files and push changes to the remote repository. 4. Sanitization: The skill does not perform any sanitization of the fetched external content.
  • [COMMAND_EXECUTION]: The skill executes local Python scripts using uv run and various GitHub CLI (gh) commands to manage Pull Request workflows.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 31, 2026, 04:05 PM