light-figure-planning

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is purely instructional and serves as a planning guide for scientific data visualization.
  • [EXTERNAL_DOWNLOADS]: Mentions various legitimate tools (matplotlib, seaborn, Inkscape, etc.) and provides links to official documentation and journal websites for reference. No suspicious or unverified downloads are present.
  • [COMMAND_EXECUTION]: Provides example CLI commands for tools like Inkscape and Mermaid for educational purposes. These are standard usage patterns and do not involve unauthorized execution.
  • [DATA_EXFILTRATION]: No patterns of sensitive file access or unauthorized data transmission were found. Mentions of 'curl' refer to historical data collection for verifying journal specifications.
  • [PROMPT_INJECTION]: The skill follows standard instructional formatting and does not attempt to bypass safety filters or override agent behavior.
  • [CREDENTIALS_UNSAFE]: No hardcoded secrets or credentials detected. The mention of 'OPENROUTER_API_KEY' in the documentation is a generic reference to an environment variable requirement for a different skill, not a leaked secret.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 05:04 AM
Security Audit — agent-trust-hub — light-figure-planning