cali-product-ads
Pass
Audited by Gen Agent Trust Hub on Jul 3, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The documentation in
references/cli-tools/provides instructions for the manual installation of external plugins and extensions from GitHub and NPM registries, includingcursor/plugins,PriNova/pi-agent-codebase-workflows, and@juicesharp/rpiv-todo. These are presented as optional environmental setup steps for the user. - [COMMAND_EXECUTION]: The reference files describe how the AI agent should interact with various CLI tools (e.g.,
agent_browser,plannotator,subagent) depending on which harness is detected (Pi, OpenCode, Claude Code, or Codex). - [SAFE]: The core skill content in
SKILL.mdconsists of static educational material about advertising stages (Pre-contemplation to Maintenance) and corresponding ad categories. The skill's configuration explicitly setsdisable-model-invocation: true, preventing the skill from triggering model actions autonomously.
Audit Metadata