decision-intelligence

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill 'decision-intelligence' is a purely instructional framework for guiding agent reasoning through six specific mental models (Expected Value, Base Rate Neglect, Sunk Cost Fallacy, Bayesian Thinking, Survivorship Bias, and Kelly Criterion).
  • [SAFE]: No executable scripts, binaries, or shell commands are present in the skill definition.
  • [SAFE]: The skill does not perform any network requests, file system modifications, or sensitive data access.
  • [SAFE]: Analysis of the text and metadata found no evidence of prompt injection, obfuscation, or persistence mechanisms.
  • [SAFE]: While the skill processes user-provided decision scenarios, it lacks any capabilities (such as tool execution or file writing) that could be exploited via indirect prompt injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 10:21 AM