research-lit

Warn

Audited by Snyk on May 2, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly performs external web searches and API fetches (Step 1: "Search (external)" — WebSearch, arXiv API, Semantic Scholar, DeepXiv, Exa) and ingests/analyses that third‑party content (including optional PDF downloads and automatic research-wiki ingest) as required workflow steps, so untrusted public content can be read and used to drive tool actions and decisions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 2, 2026, 04:27 AM
Issues
1