skills/kursku/skills/iterate-pr/Gen Agent Trust Hub

iterate-pr

Pass

Audited by Gen Agent Trust Hub on Jun 19, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its processing of external, untrusted data from GitHub PRs.
  • Ingestion points: Pull request feedback is fetched via scripts/fetch_pr_feedback.py and CI status/logs are fetched via scripts/fetch_pr_checks.py.
  • Boundary markers: The instructions do not specify any boundary markers or delimiters to separate untrusted data from system instructions.
  • Capability inventory: The agent has the capability to modify the codebase, execute git push, and post comments back to GitHub via gh api.
  • Sanitization: There is no evidence of sanitization or filtering of the external data before it is processed by the agent.
  • [COMMAND_EXECUTION]: The skill utilizes several command-line tools to perform its intended functions.
  • Evidence: The skill executes gh pr view, git add, git commit, git push, and uses uv run to execute bundled Python scripts for fetching data.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 19, 2026, 04:31 PM
Security Audit — agent-trust-hub — iterate-pr