code-review-pro

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze source code provided by users, which serves as a data ingestion surface for untrusted content. If the provided code contains malicious instructions, it could potentially influence the agent's behavior during the analysis phase.
  • Ingestion points: The skill processes code snippets provided by the user when they request a code review, security audit, or performance analysis (as defined in SKILL.md).
  • Boundary markers: The instructions do not define specific delimiters or instructions for the agent to treat the code blocks as inert data, which is a common defense against indirect injection.
  • Capability inventory: Analysis shows the skill focuses solely on generating a text-based markdown report and does not invoke dangerous system tools, network operations, or file system writes.
  • Sanitization: There are no explicit steps provided to sanitize or filter the input code before the agent processes it for analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 07:25 AM
Security Audit — agent-trust-hub — code-review-pro