code-distill
Warn
Audited by Snyk on Jul 6, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). Outsider-authored free text can enter the LLM context when the required runtime workflow performs code discovery on a user-specified GitHub repo (e.g., reading files/tests/examples and tracing imports/usages), which are authored by third parties and then ingested as readable source text.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata