visual-explainer

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

• Third-party content exposure detected (high risk: 0.90). The skill's review workflow explicitly accepts PR identifiers (e.g., "/review #42") and calls tools like "gh pr diff 42" to fetch pull request diffs from GitHub—user-generated, public content the agent reads and acts on (verifying, editing files, generating diagrams), so third-party content can materially influence tool use and decisions.