code

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

• Third-party content exposure detected (high risk: 0.70). The skill's review-and-commit workflow (see the "Update Check" step in review-and-commit.md) explicitly fetches https://raw.githubusercontent.com/abpai/skills/main/versions.json from the public web and uses that remote data to decide whether to pause and offer/run an update (e.g., npx skills update code), so it ingests open/public third-party content that can materially change subsequent tool use.