image-edit
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses
npx agent-media@latestto download and execute theagent-mediapackage from the npm registry. This represents the primary media processing utility provided by the vendor. - [COMMAND_EXECUTION]: The skill executes shell commands using
npxto perform image editing operations in the local environment. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input from external files or URLs via the
--inparameter and user-provided text via the--promptparameter. - Ingestion points: Files and URLs provided through the
--inargument and text via the--promptargument in SKILL.md. - Boundary markers: None identified in the provided command structure.
- Capability inventory: The skill executes shell commands and makes network requests to media providers.
- Sanitization: No specific input sanitization or validation logic is defined in the skill instructions.
Audit Metadata