account-intelligence

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

• Third-party content exposure detected (high risk: 1.00). The skill's PHASE 1 "RESEARCH THE ACCOUNT" workflow requires the agent to perform multiple targeted web searches and ingest public third-party content (press releases, earnings call transcripts, job postings, SAM.gov/USAJobs, news sites, vendor case studies) and explicitly uses those findings to drive downstream decisions (named champions, opportunity map, outreach, AI use cases), so it clearly consumes untrusted public content that could carry indirect prompt-injection instructions.