NYC

reviewing-pr

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • PROMPT_INJECTION (LOW): The skill is vulnerable to Indirect Prompt Injection (Category 8) as it ingests untrusted data from external sources and incorporates it into the agent's context.
  • Ingestion points: The skill reads attacker-controlled content via gh pr view, gh pr diff, and gh api in SKILL.md (Step 1).
  • Boundary markers: Absent. The instructions do not define delimiters or provide specific warnings to the agent to ignore instructions contained within the PR diffs or existing comments.
  • Capability inventory: The agent can execute shell commands (git, gh), post PR reviews/comments, and modify PR metadata (labels).
  • Sanitization: The skill employs shell-safe quoted heredocs (cat <<'EOF') when constructing comment bodies, which effectively prevents shell command injection but does not sanitize the natural language content against prompt injection.
  • COMMAND_EXECUTION (SAFE): The skill uses standard GitHub CLI (gh) and Git commands necessary for its primary purpose of PR review. Commands are well-structured and avoid dynamic execution of untrusted strings in the shell environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:29 PM