skills/product-on-purpose/thinking-framework-skills/think-expected-value-decision-tree/Gen Agent Trust Hub
think-expected-value-decision-tree
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues were detected. The skill provides guidelines for structured thinking and qualitative analysis without performing any high-risk operations.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided decision scenarios and options to generate a decision tree. While it lacks explicit boundary markers for untrusted input, it also has no capabilities to execute code, access the filesystem, or perform network operations, mitigating the risk of downstream exploitation.
- Ingestion points: User-provided decision descriptions and choice options are ingested during the framing step defined in
SKILL.md. - Boundary markers: None identified in the provided templates or instructions.
- Capability inventory: No subprocess calls, network operations, or filesystem write capabilities are present in the skill.
- Sanitization: No explicit sanitization or filtering of user-provided input is performed.
Audit Metadata