visualize

Warn

Audited by Gen Agent Trust Hub on Jul 9, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
  • [DATA_EXFILTRATION]: The skill accesses the user's home directory to read evaluation data stored in ~/.claude/.skill-evaluator/skills/.
  • [COMMAND_EXECUTION]: The workflow involves generating an HTML file in the temporary directory (/tmp/skill-up-viz.html) and executing a shell command (open) to launch the file in a web browser.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 9, 2026, 01:18 AM
Security Audit — agent-trust-hub — visualize