code-review-pro

Pass

Audited by Gen Agent Trust Hub on Sep 24, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill analyzes untrusted user code, which acts as an ingestion surface for indirect prompt injection. However, the risk is mitigated by the lack of tool access; the skill does not use network, file system, or command execution capabilities.
  • Ingestion points: User-supplied code for review (SKILL.md).
  • Boundary markers: Absent; no specific delimiters or instructions to ignore embedded commands.
  • Capability inventory: None; the skill generates text reports only.
  • Sanitization: Absent.
  • [SAFE]: The instructions are standard for the stated purpose of code review and include no indicators of malicious intent or behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 24, 2026, 12:50 AM
Security Audit — agent-trust-hub — code-review-pro