expo-cicd-workflows

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly fetches and parses public, third-party resources at runtime (notably https://api.expo.dev/v2/workflows/schema and docs from raw.githubusercontent.com) and instructs the agent to derive answers from those fetched files, so it consumes untrusted open-web content as part of its workflow.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill's runtime validator and generation logic fetches the live schema from https://api.expo.dev/v2/workflows/schema (explicitly marked "NECESSARY") and uses that fetched content as the authoritative source to drive validation and the agent's answers, so this external URL directly controls the agent's prompts/behavior at runtime.