image-face-swap
Pass
Audited by Gen Agent Trust Hub on Jun 22, 2026
Risk Level: SAFEDATA_EXFILTRATIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONCREDENTIALS_UNSAFEPROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: Transmits user-provided face images and scene images to the external Meitu OpenAPI for processing.
- [EXTERNAL_DOWNLOADS]: Downloads and installs the
meitu-clitool from the npm registry if not present or outdated. - [COMMAND_EXECUTION]: Executes the
meitucommand-line interface to interact with the Meitu API. - [CREDENTIALS_UNSAFE]: Accesses sensitive API credentials stored in
~/.meitu/credentials.jsonor environment variables for authentication with the Meitu service. - [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it processes untrusted external data that could contain instructions designed to manipulate the agent.
- Ingestion points: Data enters the context via the
head_image_url,sence_image_url, andpromptparameters. - Boundary markers: No explicit delimiters or boundary instructions are used to isolate the external inputs.
- Capability inventory: The skill executes the
meituCLI and writes resulting files to the local filesystem. - Sanitization: No validation or filtering is performed on the input prompt or external content.
Audit Metadata