systematic-review

Warn

Audited by Snyk on Mar 24, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.70). The SKILL.md explicitly instructs the agent to "Use multiple databases (Semantic Scholar, arXiv, OpenAlex)" and to screen and extract full-text content, which requires fetching and interpreting public third-party documents that could contain untrusted content influencing decisions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 24, 2026, 11:05 AM
Issues
1