attack-tree-construction
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [No Code] (SAFE): The skill consists solely of markdown instructions for manual or LLM-guided threat modeling and contains no scripts or automated components.
- [Safe Metadata] (SAFE): Metadata fields are clear and align with the instructional content of the skill.
- [Indirect Prompt Injection] (SAFE): The skill ingests user input regarding security targets, but since it lacks any external tools or file-system access, there is no risk of capability exploitation.
Audit Metadata