loss-aversion-prospect-theory
Pass
Audited by Gen Agent Trust Hub on Aug 22, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill consists entirely of markdown documentation, instructional prompts, and academic examples. There are no scripts (Python, Node.js, Shell), configuration files for tools, or executable binaries included in the package.
- [SAFE]: All external links target the vendor's official domain (deciqai.com) or academic sources. No data exfiltration patterns or sensitive file access were detected. The skill instructions follow standard behavioral coaching patterns without attempting to bypass safety filters or perform privileged operations.
- [PROMPT_INJECTION]: The skill uses instructional language such as 'IMPORTANT' and 'WAIT', but these are within the context of a legitimate 'Coach mode' for the agent to guide a user through a decision process. They do not attempt to override system safety guidelines or extract system prompts.
- [EXTERNAL_DOWNLOADS]: The skill references external URLs for additional information and examples (deciqai.com), but these are static documentation links and do not involve automated fetching of code or untrusted data during execution.
Audit Metadata