lit-search
Warn
Audited by Snyk on Mar 4, 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 explicitly queries and ingests public third-party content from the OpenAlex API and external OA/full-text URLs (see api/openalex-reference.md and phases/phase1-search.md / phase3-snowball.md / phase4-fulltext.md), requires the agent to read and interpret titles/abstracts and downloaded full texts, and uses those results to drive screening, snowballing, annotation, and follow-up actions—so untrusted web-hosted content can materially influence agent behavior.
Audit Metadata