skills/findbene/skills/cpo-advisor/Gen Agent Trust Hub

cpo-advisor

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: Detailed analysis of the skill instructions and Python scripts revealed no malicious intent, obfuscation, or safety bypass attempts.
  • [COMMAND_EXECUTION]: The skill uses local Python scripts (pmf_scorer.py, portfolio_analyzer.py) for analytical processing. These scripts are restricted to standard libraries (json, sys, argparse, math), contain no dangerous execution sinks like eval() or exec(), and do not make system or network calls. They operate purely on user-provided data inputs.
  • [DATA_EXFILTRATION]: No network capabilities are requested or used within the skill. All data processing and report generation occur within the local environment without external communication.
  • [PROMPT_INJECTION]: The skill's instructions are well-structured for product leadership tasks and do not contain patterns intended to manipulate the agent's core safety guidelines or extract system prompts.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 01:43 PM
Security Audit — agent-trust-hub — cpo-advisor