image-id-photo-generate
Pass
Audited by Gen Agent Trust Hub on Aug 29, 2026
Risk Level: SAFEDATA_EXFILTRATIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill reads API credentials from
~/.meitu/credentials.jsonto authenticate with the vendor's OpenAPI service. - [COMMAND_EXECUTION]: The skill uses the
meituCLI tool to execute image processing commands. - [EXTERNAL_DOWNLOADS]: The documentation describes installing the
meitu-clipackage from the npm registry as a prerequisite. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied images and incorporates descriptions into prompt templates for ID photo generation. This introduces a surface where malformed input could potentially influence the model's output instructions.
- Ingestion points: The
image_urlparameter receives untrusted data from the user. - Boundary markers: The prompt templates lack explicit delimiters or instructions to ignore embedded content in processed data.
- Capability inventory: The skill utilizes the
meituCLI for image generation and writes the resulting files to the local file system. - Sanitization: No validation or sanitization is performed on the user-provided image data before it is described and used in the generation prompt.
Audit Metadata