draft-survey

Warn

Audited by Snyk on Jul 7, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.75). SKILL.md’s required runtime workflow (“Gather candidates broadly” via find-papers across DBLP/Crossref/Semantic Scholar/arXiv, then “Verify every entry” via verify-citations) necessarily ingests outsider-authored free text/metadata from public web/scholarly sources into the LLM context for ranking/drafting, creating an indirect prompt-injection risk.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 7, 2026, 01:02 PM
Issues
1
Security Audit — snyk — draft-survey