NYC

docs-review

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • Prompt Injection (LOW): Detected surface for indirect prompt injection (Category 8). The skill ingests untrusted data from documentation files and pull request diffs which could contain malicious instructions.\n- Ingestion points: Markdown files and GitHub PR diffs (via mcp__github__get_pull_request_diff).\n- Boundary markers: Absent. The instructions do not define delimiters or ignore markers for external content.\n- Capability inventory: Access to Bash tool, Read, Grep, and GitHub review creation tools.\n- Sanitization: Absent. Content is processed directly without filtering.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:29 PM