karpathy-review

Pass

Audited by Gen Agent Trust Hub on Aug 5, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues were identified in this skill. The skill acts as a set of instructions for the agent's behavior during code review.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data such as coding plans and git diffs.
  • Ingestion points: The skill accepts a 'plan' (files to change, abstractions) and 'diff' (git output) as input in SKILL.md.
  • Boundary markers: The instructions do not define specific delimiters for untrusted input.
  • Capability inventory: The skill does not possess capabilities like file system writes, network requests, or command execution.
  • Sanitization: No input sanitization or validation logic is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 5, 2026, 04:49 PM
Security Audit — agent-trust-hub — karpathy-review