literature-review

Warn

Audited by Snyk on May 14, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 1.00). The skill's "Search strategy" in SKILL.md explicitly requires querying public sources (Semantic Scholar, web search, videos, Wikipedia/Scholarpedia) and instructs the agent to read and incorporate those sources into the literature review, so untrusted third-party content can directly influence findings and downstream actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 14, 2026, 08:51 AM
Issues
1