grok
Warn
Audited by Snyk on Jul 3, 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 runtime path is that
grok::run/grok::startspawns the hostgrokCLI, which streams Grok-generated event text back intogrok::events/agent::events; this is outsider-authored free text because it originates from the xAI Grok service (not the operating user) and is ingested into the agent’s LLM context via the streamed event frames.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata