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 Nov 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSNO_CODE
Full Analysis
- [SAFE]: The skill is a non-executable thinking framework designed to structure decision-making processes. No malicious logic, persistence mechanisms, or privilege escalation attempts were detected.\n- [INDIRECT_PROMPT_INJECTION]: The skill defines an ingestion surface for processing external decision data (options and probabilities). However, the skill has no dangerous capabilities that could be exploited via injection, as it lacks network, file system, or command execution access.\n
- Ingestion points: User-provided options, outcomes, and probabilities defined in SKILL.md.\n
- Boundary markers: None explicitly defined in instructions.\n
- Capability inventory: Restricted to text generation and logical reasoning; no subprocess or network tools are present.\n
- Sanitization: No input validation is specified.\n- [EXTERNAL_DOWNLOADS]: The skill metadata and documentation include a reference to the author's official GitHub repository for attribution purposes.\n
- Evidence: Reference to https://github.com/product-on-purpose/thinking-framework-skills in SKILL.md.\n- [NO_CODE]: The skill consists entirely of descriptive Markdown files and YAML configuration. No Python, Node.js, or shell scripts are included in the package.
Audit Metadata