iblai-agent-datasets
Warn
Audited by Snyk on Jun 13, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). The skill’s runtime reads/writes include adding external resources via
POST .../documents/train/withtype=url|youtube|webcrawler|github(and then pollingGET .../documents/pathways/{mentor}/), so outsider-authored free text from those URLs/pages/repo content can be ingested into the agent’s RAG context through the platform’s training pipeline.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata