create-structure-outline
Pass
Audited by Gen Agent Trust Hub on May 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized access attempts were identified in the skill's instructions or logic.
- [PROMPT_INJECTION]: Evaluated for indirect prompt injection risks (Category 8):
- Ingestion points: Reads user-provided design documents (
thoughts/shared/design/) and referenced research files. - Boundary markers: Absent; the skill does not explicitly instruct the model to ignore instructions embedded within the design documents.
- Capability inventory: File writing (Markdown and HTML) to
thoughts/shared/structure/. No network or shell execution capabilities are utilized. - Sanitization: Not explicitly performed. However, the risk is negligible as the skill lacks high-privilege capabilities or network exit points.
Audit Metadata