messages-ops

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs the agent to retrieve one-time codes from message surfaces and return the exact "message summary or code" verbatim, which requires handling secrets in output.

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

• Third-party content exposure detected (high risk: 0.85). The “Messages Ops” workflow is explicitly for live-message retrieval (iMessage/DMs/one-time codes/thread inspection), which at runtime would ingest the contents of messages authored by other people (e.g., X/social DMs or iMessage threads) into the agent’s LLM context.