grok-media
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions define a workflow that ingests untrusted external data, creating an indirect prompt injection surface.
- Ingestion points: Public HTTPS URLs for images and user-provided natural language prompts are processed by the agent to interact with the xAI API (SKILL.md).
- Boundary markers: The instructions do not define delimiters or "ignore" blocks for external content to prevent instructions in inputs from being executed.
- Capability inventory: The skill facilitates network operations (API calls) and remote media processing.
- Sanitization: No validation or sanitization requirements are defined for the input URLs or prompt content.
- [SAFE]: Authentication is handled using environment variables (XAI_API_KEY), which is a secure method for managing sensitive credentials.
- [SAFE]: All referenced API endpoints belong to xAI, a well-known and legitimate service provider.
- [NO_CODE]: The skill consists entirely of instructional markdown and does not include any executable scripts, binaries, or external dependencies.
Audit Metadata