living-ui-manager

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the run_shell action to execute a local TypeScript CLI tool (cli.ts) via Node.js. This tool is located within the vendor's repository structure (living-ui/tools/src/cli.ts) and is used for project discovery, data operations, and running defined project verbs.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data that could potentially contain malicious instructions intended to influence the agent's behavior.
  • Ingestion points: The skill reads LIVING_UI.md, manifest.json, pocketbase.log, and frontend_console.log from various project directories.
  • Boundary markers: The instructions do not specify the use of boundary markers or delimiters when the agent reads or interprets these external files.
  • Capability inventory: The skill possesses shell execution capabilities (run_shell) and the ability to make local HTTP requests (living_ui_http).
  • Sanitization: There is no evidence of content sanitization or validation for the data ingested from logs or project documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 01:51 PM
Security Audit — agent-trust-hub — living-ui-manager