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
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 10, 2026, 03:25 AM
Issues
1
Security Audit — snyk — csag-extraction