image-generate
Pass
Audited by Gen Agent Trust Hub on Mar 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill triggers the
agent-mediaCLI tool to facilitate image creation. This is the primary intended capability and involves a vendor-related tool. - [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface. Ingestion points: The
--promptinput inSKILL.md. Boundary markers: No delimiters or ignore instructions are present. Capability inventory: Execution of theagent-mediaCLI tool. Sanitization: Input sanitization is not specified. This surface is expected for the skill's primary function.
Audit Metadata