nexu-e2e-test
Warn
Audited by Snyk on Jul 9, 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). The required workflow’s “Connected Channel (Slack/Discord)” path ingests outsider-authored free-form messages from other users into the gateway’s auto-reply pipeline (dispatchInboundMessage() → ensureSkillSnapshot()), which then feeds into the LLM context via the generated system prompt (skillsSnapshot.prompt / available_skills).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata