research-pipeline

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: 0.90). The skill's researcher stage (SKILL.md "Researcher executes: Literature search via PubMed, bioRxiv, OpenAlex" and "Paper reading and note-taking") explicitly fetches and ingests public third-party articles which the agent reads and uses to drive downstream decisions in the pipeline, exposing it to untrusted external content that could carry indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 28, 2026, 06:30 AM