pr-review

Pass

Audited by Gen Agent Trust Hub on Mar 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill workflow involves executing shell commands like git diff and gh pr diff <number>. Using user-provided identifiers like pull request numbers directly in shell commands poses a risk of command injection if the underlying execution environment does not adequately sanitize arguments.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted data (git diffs and PR content) that could contain malicious instructions designed to subvert the agent's review process.
  • Ingestion points: Data retrieved via git diff and gh pr diff as described in SKILL.md Phase 1.
  • Boundary markers: The instructions lack explicit delimiters or safety prompts to prevent the agent from following instructions embedded within the reviewed code diffs.
  • Capability inventory: The skill can execute CLI tools (git, gh) and access local files (e.g., CLAUDE.md).
  • Sanitization: There is no specified logic for sanitizing or filtering the content of the diffs before they are processed by the review methodologies.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 7, 2026, 08:15 PM