stormboard

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

• Third-party content exposure detected (high risk: 0.70). The SKILL.md instructs the agent to connect to Stormboard via the Membrane CLI and to list/run actions that return Stormboard workspace/idea content (user-generated third‑party data) which the agent is expected to read and act on, so untrusted third‑party content could influence subsequent tool use.