figure-it-out
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of high-level procedural instructions for task management. It contains no executable scripts, shell commands, network operations, or sensitive file access.
- [INDIRECT_PROMPT_INJECTION]: The skill processes arbitrary user tasks, creating a surface for indirect prompt injection.
- Ingestion points: User-provided task descriptions at runtime in the main skill body.
- Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the user task.
- Capability inventory: The skill references other components like
architectandshow-me-your-workfor its workflow, butfigure-it-outitself does not invoke tools directly as indicated by its configuration. - Sanitization: No input validation or sanitization of user-provided task descriptions is specified.
Audit Metadata