adversarial-review

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill defines an adversarial review process that is exposed to indirect prompt injection via the untrusted code it is designed to analyze.
  • Ingestion points: The process ingests external codebases, applications, and diffs provided for review (SKILL.md).
  • Boundary markers: No instructions are provided to use delimiters or safety warnings to ignore instructions embedded within the analyzed content (SKILL.md).
  • Capability inventory: The agent is instructed to run the target code to reproduce findings and spawn subagents based on its analysis (SKILL.md).
  • Sanitization: No input validation or sanitization of the target code is performed before analysis or execution (SKILL.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 02:27 PM
Security Audit — agent-trust-hub — adversarial-review