skills/planetabhi/skills/ship-ui/Gen Agent Trust Hub

ship-ui

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill implements standard developer workflow tasks using git commands. It audits code changes for accessibility, performance, and security without performing unauthorized network operations or accessing sensitive user credentials outside the repository scope.
  • [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted content from git diffs. 1. Ingestion points: The skill reads output from git diff and git status to evaluate code changes (SKILL.md). 2. Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions for the ingested diff data. 3. Capability inventory: The skill generates commit messages and pull request descriptions based on the provided diffs. 4. Sanitization: No sanitization or filtering of the diff content is defined.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 07:20 AM
Security Audit — agent-trust-hub — ship-ui