grok-prompting

Warn

Audited by Snyk on Feb 16, 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 explicitly instructs the agent to leverage Grok's real-time access to X (Twitter) and built-in web search to read and summarize social-media posts and public web content (e.g., "give me the vibe from Crypto Twitter" and "based on what people are discussing on X"), which are untrusted, user-generated third-party sources the agent is expected to ingest and interpret.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 02:25 AM