pd-github

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

• Third-party content exposure detected (high risk: 0.80). This skill fetches and displays user-generated content from the public GitHub API (api.github.com) — e.g., repository files (file), issues (issues, search), and PRs (prs, pr-summary) — which the agent is expected to read/interpret as part of its workflow and which can influence follow-up actions (comment, create-pr, write-file), creating a pathway for indirect prompt injection.