skills/wubin1836/ai-ecommerce-expert-agent-skills/ai-ecommerce-expert-video-result-management/Gen Agent Trust Hub
ai-ecommerce-expert-video-result-management
Warn
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: MEDIUMREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The helper script
scripts/imiva_mcp.pyexecutesnpx -y @infimind/ecom-content-cli@latest, which dynamically downloads and runs code from the NPM registry during execution. The use of the@latesttag means the code being executed can change without notice. - [COMMAND_EXECUTION]: The Python script
scripts/imiva_mcp.pyusessubprocess.Popento launch the Node.js runtime and execute the MCP package, establishing a bi-directional communication channel through standard streams. - [EXTERNAL_DOWNLOADS]: The skill connects to the external NPM registry to fetch the required CLI tool and interacts with the API host
imiva.ecpro.comfor task management operations. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests and processes data from external task results.
- Ingestion points: Data retrieved from the
get_user_taskstool call processed inscripts/imiva_mcp.py. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the script or instructions.
- Capability inventory: The skill possesses command execution capabilities through its Python helper script.
- Sanitization: There is no evidence of sanitization or validation performed on the external task data before it is presented to the agent.
Audit Metadata