omh-award-bar-score
Pass
Audited by Gen Agent Trust Hub on Nov 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill involves processing external web content (URLs and rendered captures), which creates an attack surface for indirect prompt injection. * Ingestion points: target URL and rendered captures in SKILL.md. * Boundary markers: None specified. * Capability inventory: No dangerous capabilities; the skill explicitly forbids network or browser execution. * Sanitization: None specified.
- [SAFE]: No signs of obfuscation, remote code execution, or unauthorized data access were detected. The skill is documentation-based and contains no scripts.
Audit Metadata