dspy-data
Warn
Audited by Snyk on May 2, 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 loads public, user-contributed datasets from HuggingFace (e.g., load_dataset("hotpotqa", ...") in SKILL.md and examples.md), which the agent ingests and uses to train/optimize models—third-party content that can materially influence model behavior and tool use.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata