dspy-retrieval
Warn
Audited by Snyk on Mar 17, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill explicitly supports querying external ColBERTv2 servers via arbitrary URLs (e.g., the example public ColBERTv2 Wikipedia endpoint at http://20.102.90.50:2017/wiki17_abstracts) and then passes the retrieved passages into generation/RAG pipelines, so untrusted public third‑party content can directly influence model behavior.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill's examples configure dspy.ColBERTv2 to use the runtime URL http://20.102.90.50:2017/wiki17_abstracts, which the retriever queries at runtime and injects the returned passages into the model context (directly controlling prompts), so the skill depends on that external content when used this way.
Issues (2)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
Audit Metadata