058-design-bdd
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external "behavior facts" and "outsider-authored scenario prose" as requirement data. This creates a surface for indirect prompt injection where malicious instructions could be embedded in the input data. However, the risk is negligible because the skill does not employ any executable tools, network operations, or file system modifications that could be abused. Additionally, the instructions require the use of "maintainer-sanitized" facts.
- Ingestion points:
SKILL.md(Workflow Step 1) - Boundary markers: Absent
- Capability inventory: None (only text generation)
- Sanitization: The skill mandates using maintainer-sanitized behavior facts.
Audit Metadata