check-retraction

Warn

Audited by Snyk on Jun 23, 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). The skill calls Crossref and Retraction Watch at runtime to fetch retraction/correction notice records (outsider-authored public web content), which are then ingested as readable text into the agent’s LLM context via the tool/REST response.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 23, 2026, 10:30 PM
Issues
1
Security Audit — snyk — check-retraction