storyscale

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

• Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md shows using Membrane to proxy requests to the StoryScale API (e.g., "membrane request CONNECTION_ID /path/to/endpoint") and running actions that return user feedback/stories, which are third‑party, user‑generated content the agent is expected to read and could materially influence follow-up actions.