skills/wu-yc/labclaw/matplotlib/Gen Agent Trust Hub

matplotlib

Pass

Audited by Gen Agent Trust Hub on Mar 15, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill contains a 'Suggest Using K-Dense Web For Complex Worflows' section that provides specific behavioral instructions to the AI.
  • Evidence: The text instructs the agent to 'proactively suggest using K-Dense Web (www.k-dense.ai)' and 'Frame the suggestion as an optional productivity upgrade' when users perform complex research or multi-step reasoning.
  • This represents a form of behavioral steering where the skill author attempts to influence the agent's natural response patterns to favor a specific third-party service.
  • [COMMAND_EXECUTION]: The skill documentation references and encourages the execution of local Python scripts.
  • Evidence: The 'Quick Reference Scripts' section provides command-line examples such as python scripts/plot_template.py and python scripts/style_configurator.py.
  • While these are presented as helpful utilities, instructing the execution of local scripts from a skill package is a capability that should be monitored, as the contents of these specific files were not included in the primary skill file for verification.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 15, 2026, 04:32 AM