dispatch

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill requires reading 64-char circle keys from dispatchconfig.yml and using them verbatim in Authorization: Bearer {key} headers (and presents examples with the key in requests), which forces the LLM to handle and potentially output secret values directly — an exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.80). This skill explicitly fetches and ingests user-generated answers from the third-party API at api.peepsapp.ai (see SKILL.md GET /dispatch and GET /inbox responses), and those returned "text" fields are read and presented by the agent as part of its workflow, so untrusted third-party content can influence decisions or follow-up actions.