agentaddress

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill prompt instructs the agent to save and use a bearer token (credentials.read_token) returned from an API response in subsequent HTTP Authorization headers, which requires the LLM to handle and output a secret value directly.

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

• Third-party content exposure detected (medium risk: 0.30). The required workflow includes reading inbound messages, webhooks, and emails from an event queue (endpoints.events_url) that any outsider can post to if given the address.