expert-munger

Pass

Audited by Gen Agent Trust Hub on Nov 2, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists of instructional and reference markdown files providing cognitive frameworks. No executable code, scripts, or malicious patterns were detected across the skill's components.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user investment and business queries (ingestion surface). While it lacks explicit boundary markers for untrusted data, its capabilities are strictly advisory and reasoning-based, with no file-write or network-exfiltration capabilities that could be exploited via injection. The risk is assessed as safe.
  • [EXTERNAL_DOWNLOADS]: The documentation references reputable external resources for educational purposes, including Amazon, YouTube, and Stripe Press. These are well-known services and do not represent a security risk.
  • [COMMAND_EXECUTION]: The documentation mentions the use of npx openskills as a suggested method to load the expert module. This is interpreted as standard platform-specific tooling for managing agent skills and does not involve malicious command injection or unauthorized execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 2, 2026, 08:24 AM