github

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs the agent to connect to GitHub via the Membrane connector and run actions like list-issues, get-issue, list-pull-requests, and create-issue-comment, so the agent will fetch and interpret user-generated, public GitHub content (issues/PRs/comments) that could contain instructions influencing subsequent actions.