plot-keypoints
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- [Indirect Prompt Injection] (INFO): The skill processes untrusted story text for analysis. Mandatory Evidence Chain: 1. Ingestion points: story text processed via 'Read' tool; 2. Boundary markers: none; 3. Capability inventory: 'Read' tool only; 4. Sanitization: none. Capability Tier is INFO because output is for display only with no write or external communication capabilities.
- [No Code] (SAFE): The skill consists entirely of markdown instructions with no scripts, binaries, or package dependencies.
Audit Metadata