image-gen
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill defines a workflow where the agent executes the
imagenCLI tool to generate visual assets. This usage is transparent and central to the skill's purpose. - [INDIRECT_PROMPT_INJECTION]: The skill involves analyzing potentially untrusted article content to create image generation prompts. This represents a standard surface for indirect injection.
- Ingestion points: Article content identified in the initial analysis phase (SKILL.md).
- Boundary markers: None specified for the input article text.
- Capability inventory: Execution of the
imagen generateshell command (SKILL.md). - Sanitization: No specific filtering or escaping for the generated prompts is described.
Audit Metadata