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.py executes npx -y @infimind/ecom-content-cli@latest, which dynamically downloads and runs code from the NPM registry during execution. The use of the @latest tag means the code being executed can change without notice.
  • [COMMAND_EXECUTION]: The Python script scripts/imiva_mcp.py uses subprocess.Popen to 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.com for 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_tasks tool call processed in scripts/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
Risk Level
MEDIUM
Analyzed
Aug 25, 2026, 08:01 AM
Security Audit — agent-trust-hub — ai-ecommerce-expert-video-result-management