context-degradation
Warn
Audited by Snyk on Jun 30, 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’s runtime workflow ingests the agent’s current
context/context string(e.g., passed intoContextHealthAnalyzer.analyze(context, ...)andPoisoningDetector.detect_poisoning(context)), and that context commonly includes outsider-authored free text such as prior user messages or retrieved web/document content; the skill itself does not filter provenance before feeding it into the LLM.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata