projects-dashboard

Pass

Audited by Gen Agent Trust Hub on Jul 25, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute a Python script named render-dashboard.py and uses system utilities like open or xdg-open to present the generated HTML dashboard to the user.
  • [DYNAMIC_EXECUTION]: The execution path for the dashboard script is resolved dynamically at runtime by executing a shell command to search the agent's plugin cache for the latest version of the cogni-projects directory.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests external project portfolio and assignment records (JSON files). While these files are untrusted, the skill is designed for read-only visualization and manages data mismatched through a warning system rather than allowing them to alter execution logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 25, 2026, 01:51 PM
Security Audit — agent-trust-hub — projects-dashboard