woodpeckerco

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 instructs the agent to fetch and interact with data from the Woodpecker.co service (via membrane action list/run and the "membrane request CONNECTION_ID /path/to/endpoint" proxy), which will retrieve user-generated/untrusted third-party content that the agent is expected to read and act on, enabling indirect prompt injection.