omniroute-image
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text for image generation prompts, which are then transmitted to external providers via network requests. 1. Ingestion points: The 'prompt' field in the POST request body defined in SKILL.md. 2. Boundary markers: No delimiters or protective instructions are used to separate the user-provided prompt from the surrounding JSON structure or to prevent instruction injection. 3. Capability inventory: Shell command execution via curl and jq for network interaction and data processing. 4. Sanitization: The skill does not implement or describe any sanitization, filtering, or safety checks for the content of the prompt field.
- [EXTERNAL_DOWNLOADS]: The skill references an external resource for setup instructions, specifically a SKILL.md file hosted on a third-party GitHub repository (diegosouzapw/OmniRoute).
- [COMMAND_EXECUTION]: The instructions rely on shell commands (curl, jq) to perform discovery and image generation tasks, including the interpolation of environment variables ($OMNIROUTE_URL, $OMNIROUTE_KEY) into these commands.
Audit Metadata