conf-abstract-enrichment

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

• Third-party content exposure detected (high risk: 0.85). The skill’s runtime web search (Pattern 2/Workflow Step 3) fetches public pages (e.g., linked repos/papers/speaker/company pages) and ingests their readable text into the LLM to draft abstract_enriched and axis_updates, which is an outsider-authored free-text source path.