skills/cogni-work/insight-wave/features/Snyk

features

Warn

Audited by Snyk on Jul 25, 2026

Risk Level: MEDIUM

Full Analysis

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

Third-party content exposure detected (high risk: 0.75). Yes—during Deep Dive (optional/triggered) the required workflow delegates “web research” and/or “Explore” on user-provided URLs/documents, which can ingest outsider-authored free text into the LLM context via the web/extraction agent and then feed its findings into Phase 3–4.

Issues (1)

W011

MEDIUM

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

Audit Metadata

Risk Level

MEDIUM

Analyzed

Jul 25, 2026, 01:51 PM

Issues

1

Security Audit — snyk — features