executive-mentor

Pass

Audited by Gen Agent Trust Hub on Jul 18, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists of instructional content and local utility scripts designed for executive coaching.
  • [COMMAND_EXECUTION]: The skill provides Python scripts for decision analysis. Evidence: scripts/decision_matrix_scorer.py and scripts/stakeholder_mapper.py. These scripts utilize standard libraries (json, argparse, sys) to process local or interactive input and provide formatted output without network or sensitive file access.
  • [PROMPT_INJECTION]: The skill uses instructional language to establish an adversarial coaching persona. Evidence: SKILL.md defines the 'Executive Mentor' persona and 'Adversarial Reasoning' technique. Analysis confirms these instructions focus on task performance and do not include attempts to override safety guardrails or extract system configurations.
  • [EXTERNAL_DOWNLOADS]: No external dependencies or remote script executions are present. All tools and references are contained within the skill folder.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 18, 2026, 04:18 PM
Security Audit — agent-trust-hub — executive-mentor