linkpix-shein-image
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEREMOTE_CODE_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill downloads Node.js binaries and checksum files from official sources (nodejs.org) or well-known mirrors (npmmirror.com). It implements a verification step using
sha256sum -c -to ensure file integrity before extraction. - [COMMAND_EXECUTION]: Installs the vendor-specific CLI tool
@iqinghu/qhkitglobally using the Node Package Manager (npm). It also provides instructions for setting environmental paths and shell profiles to enable tool execution. - [DYNAMIC_EXECUTION]: Employs runtime execution of Python scripts via
python -c(using the Pillow library) and Node.js tools vianpx sharp-clifor image processing and compression tasks. - [INDIRECT_PROMPT_INJECTION]:
- Ingestion points: The skill ingests untrusted user content through
uploadedImagesand natural languagepromptparameters inSKILL.md. - Boundary markers: No specific prompt delimiters or instructions to ignore embedded commands are present in the task execution templates.
- Capability inventory: The skill has the capability to execute shell commands (
qhkit), perform network operations (image generation API), and write files to the local system (image compression). - Sanitization: There is no explicit sanitization or validation of the user-provided prompt or image metadata before processing.
Audit Metadata