inkos-long-market-research

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

• Third-party content exposure detected (low risk: 0.10). The required runtime workflow for this skill focuses on using research_web (for current claims) and optionally ingest_material (for user-provided reports/URLs), but the provided skill files do not specify any monitored outsider-authored feed/queue that would be ingested without the agent first selecting specific content.