detecting-ai-code
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE] (SAFE): The skill is composed exclusively of Markdown files (SKILL.md and evaluation scenarios). There are no scripts, binaries, or configuration files that facilitate code execution.
- [SAFE] (SAFE): Analysis of the 10 threat categories shows no evidence of credential harvesting, data exfiltration, or persistence.
- [PROMPT_INJECTION] (SAFE): Instructional phrases found in the evaluation files are context-appropriate for testing the agent's detection logic and do not attempt to bypass safety filters or override system-level instructions.
Audit Metadata