code-reviewer

Fail

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: HIGHPROMPT_INJECTIONNO_CODE
Full Analysis
  • Indirect Prompt Injection (HIGH): The skill instructs the agent to perform deep analysis on code which may contain malicious instructions designed to hijack the agent's behavior.
  • Ingestion points: External code blocks (implied by the review purpose in SKILL.md).
  • Boundary markers: Absent; there are no instructions for the agent to use delimiters or to disregard instructions found within the code being reviewed.
  • Capability inventory: Coding agents using this skill typically have high-privilege tools for file manipulation and command execution.
  • Sanitization: Absent; the instructions do not include steps to sanitize or filter comments or string literals that might contain injection attacks.
  • No Executable Code (SAFE): The skill consists entirely of markdown and metadata, with no scripts, binaries, or dependency files provided.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 16, 2026, 01:08 PM