eval-clarity
Pass
Audited by Gen Agent Trust Hub on Feb 19, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [NO_CODE] (SAFE): The skill consists entirely of natural language instructions and lacks any executable scripts or binary dependencies.
- [PROMPT_INJECTION] (LOW): The skill accepts untrusted text for evaluation without using boundary markers. Ingestion points: assistant response text in SKILL.md. Boundary markers: Absent. Capability inventory: None. Sanitization: Absent. This creates a surface for indirect prompt injection, though the impact is limited to the evaluation outcome as no dangerous tools are available.
Audit Metadata