dify-knowledge-base-upload
Warn
Audited by Snyk on Mar 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The skill makes live requests to an external Dify deployment (the
${DIFY_API_BASE_URL}/datasets/${DIFY_DATASET_ID}/metadataand upload endpoints referenced in scripts/upload_to_dataset.py and SKILL.md) and parses those JSON responses (metadata fields and upload responses) at runtime to resolve metadata and decide whether to call the metadata-write endpoint, so untrusted third‑party content from the dataset can materially influence subsequent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata