NYC
skills/getsentry/skills/code-review/Gen Agent Trust Hub

code-review

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • Prompt Injection (SAFE): The skill contains only advisory instructions for code review and does not include any patterns designed to bypass agent safety filters or override system instructions.
  • Data Exposure & Exfiltration (SAFE): No hardcoded credentials, sensitive file paths, or unauthorized network operations were found. The single external link refers to official Sentry developer documentation.
  • Unverifiable Dependencies & Remote Code Execution (SAFE): This skill provides no executable scripts, shell commands, or package dependencies (Python or Node.js).
  • Indirect Prompt Injection (SAFE): The skill's purpose is to review untrusted code, which is a known ingestion point for indirect prompt injection. However, since the skill has no executable capabilities, the risk is negligible.
  • Ingestion points: Pull request diffs and code changes (implied by description).
  • Boundary markers: None specified in the markdown instructions.
  • Capability inventory: None (The skill contains no code files or tools).
  • Sanitization: None specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 04:59 PM