csag-extraction
Warn
Audited by Snyk on Aug 10, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The skill’s runtime workflow (as described in SKILL.md) consumes the provided manuscript “full manuscript” source text to extract claims/evidence and ground them to TextSpans, meaning outsider-authored text can be ingested whenever a user supplies an arbitrary manuscript/markdown to the pipeline.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata