domain-discover

Pass

Audited by Gen Agent Trust Hub on Jul 3, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill analyzes external data from the codebase, creating a surface for indirect prompt injection.
  • Ingestion points: Step 1 performs a codebase scan of source files and documentation.
  • Boundary markers: The execution is structured using XML-like tags and blocking phase gates to ensure controlled processing.
  • Capability inventory: Uses Bash, Read, Glob, and Grep for local project operations.
  • Sanitization: Instructions specify using a dedicated CLI tool (maestro) for registrations, which limits the potential for arbitrary command execution from codebase content.
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute maestro CLI commands for discovery and registration. These operations are constrained to the local project environment and specific internal paths.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 3, 2026, 08:44 AM
Security Audit — agent-trust-hub — domain-discover