research-question-validator

Warn

Audited by Snyk on Jun 17, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.85). At runtime the skill runs 4–5 Consensus searches and then ingests the returned paper abstracts/metadata (outsider-authored scholarly content from the public web via Consensus) into the agent’s LLM context for synthesis and quoting.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 17, 2026, 03:09 PM
Issues
1
Security Audit — snyk — research-question-validator