openalex

Warn

Audited by Snyk on Feb 28, 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 explicitly ingests public OpenAlex content (e.g., the payload field returned by scry.openalex_find_works, scry.openalex_works.payload, and mv_openalex_papers/preview) and the SKILL.md workflow/recipes (reading-list builder, rerank handoff, semantic search) require the agent to read and act on that untrusted third‑party text, so third‑party payloads could indirectly inject instructions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 28, 2026, 08:31 AM