apilookup

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

• Third-party content exposure detected (high risk: 0.85). The skill’s Tier 2/3 runtime path performs WebFetch/WebSearch against external documentation/release URLs (e.g., docs_url/changelog_url from registry.json), which can ingest outsider-authored free text from public web pages into the LLM context.