siem-rules

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

• Third-party content exposure detected (medium risk: 0.30). In skill “siem-rules”, the agent’s required workflow is to process user-supplied free text context such as SIEM query drafts, log samples, and detection logic descriptions (explicitly stated in the Prompt Injection Safety Notice), which the LLM ingests at runtime without needing to select a specific item first.