security-review

Pass

Audited by Gen Agent Trust Hub on Aug 30, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external code, which provides an entry point for indirect prompt injection if the code contains malicious instructions targeted at the agent.
  • Ingestion points: The agent is instructed to review 'current code' provided in the context.
  • Boundary markers: The instructions do not specify any delimiters or safety markers to separate code from instructions.
  • Capability inventory: No tool usage or executable scripts are defined within the skill file itself, and the frontmatter explicitly disables model invocation, limiting automated execution potential.
  • Sanitization: There are no instructions for sanitizing or filtering the content of the analyzed code.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 30, 2026, 10:29 PM
Security Audit — agent-trust-hub — security-review