novelty-assessment

Warn

Audited by Snyk on Feb 20, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). The skill's workflow (SKILL.md Step 2: "Search Semantic Scholar / arXiv / OpenAlex" and "Review top-10 results with abstracts") and included script (search_semantic_scholar.py) explicitly fetch and have the agent read public third-party paper abstracts, which are untrusted content that materially influence novelty decisions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 20, 2026, 05:23 AM