expert-kahneman

Pass

Audited by Gen Agent Trust Hub on Apr 3, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill's documentation mentions using 'npx' to fetch the 'openskills' package, which is the vendor's tool for managing expert modules. This is a standard and expected behavior for this specific toolset.
  • [COMMAND_EXECUTION]: Provides command-line examples for informational purposes to show how to load and read expert modules using the 'openskills' CLI.
  • [DATA_EXFILTRATION]: No patterns indicative of sensitive data access or unauthorized external transmission were found.
  • [PROMPT_INJECTION]: No instructions attempting to bypass safety filters or override agent behavior were detected.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a process for analyzing user-supplied narratives to detect cognitive biases. (1) Ingestion points: User-provided decision scenarios. (2) Boundary markers: Absent. (3) Capability inventory: The skill does not include any tools for file writing, system execution, or network communication that could be triggered by input. (4) Sanitization: Not applicable for this text-analysis use case.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 3, 2026, 04:21 PM