trigger-getting-started

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt instructs the agent to ask the user for the project's DEV secret key and to place that secret into configuration files (e.g., a .env or trigger.config), which requires the LLM to receive and potentially emit the secret verbatim — a direct exfiltration risk.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.80). The instructions explicitly tell the user to run commands that fetch-and-execute remote packages (e.g., "npx trigger.dev@latest init" and "npx trigger.dev@latest dev", and "npm add @trigger.dev/sdk@latest"), which at runtime download and execute code from the npm registry—an external dependency that directly executes remote code.