skills/cursor/plugins/review-and-ship/Gen Agent Trust Hub

review-and-ship

Pass

Audited by Gen Agent Trust Hub on May 2, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill performs standard version control operations using the git CLI for repository management and code review.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted code diffs, creating an exposure to indirect prompt injection.
  • Ingestion points: Untrusted data enters the context through git diff output as described in SKILL.md.
  • Boundary markers: No explicit delimiters are present to isolate the diff output from the instruction context.
  • Capability inventory: Capabilities are restricted to standard Git operations (fetch, diff, status, commit, push) with no identified high-risk functions.
  • Sanitization: No content sanitization or validation of the diff output is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
May 2, 2026, 04:59 PM