grok-bot-x-search
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external, attacker-controlled sources (X/Twitter posts).
- Ingestion points: Content is retrieved from external X (Twitter) searches as described in SKILL.md.
- Boundary markers: The skill lacks explicit structural delimiters for external content, though it provides logical instructions to "Separate what an author claims from independently established facts."
- Capability inventory: While the skill itself does not define specific code execution tools, it is intended to guide the usage of search agents (Grok Bot) and shape the final delivery of potentially malicious external data.
- Sanitization: No technical sanitization (escaping or filtering) of the external content is specified beyond logical assessment.
Audit Metadata