setup

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly asks the user to paste their API key and instructs the agent to insert that key verbatim into a .env file (and echo/save it), forcing the LLM to receive and output secret values directly.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill's Step 5 "Profile Research" explicitly instructs the agent to search and ingest public sources (e.g., company website, LinkedIn) about the user and then use those findings to populate the user's profile/configuration, which exposes the agent to untrusted, user-generated third-party content that can influence its behavior.