make-local-route

Pass

Audited by Gen Agent Trust Hub on Jun 23, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses curl to perform API requests and playwright-cli to automate browser interactions for retrieving IDs and tokens from the development dashboard.
  • [PROMPT_INJECTION]: The skill processes untrusted data from local source code files and API responses, which constitutes an indirect prompt injection surface.
  • Ingestion points: Local Elixir files (e.g., lib/surge_web/router.ex, controllers, LiveViews) and JSON responses from api.jason.surge-eng.com.
  • Boundary markers: No specific delimiters or instructions to ignore embedded content are defined in the prompt logic.
  • Capability inventory: The agent has the ability to read local files, execute network requests via curl, and perform browser automation via playwright-cli.
  • Sanitization: There is no evidence of sanitization or validation of the data retrieved from external files or API endpoints before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 23, 2026, 03:07 AM
Security Audit — agent-trust-hub — make-local-route