byted-kickart-overseas-viral-replicator

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly instructs the agent to ask users to provide their AccessKey and SecretKey and to "configure it in the system environment variables" (continuing without manual terminal operations), which requires the agent to receive and likely emit those secret values verbatim, creating an exfiltration risk.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). Outsider-authored free text is ingested at runtime via user-provided product_url/image URL inputs and language fields, which are then passed into the scripts/kickart.py submit flow and further used by scripts/metrial.py pipeline/upload without any step that restricts/filters the text content beyond basic validation (e.g., domain checks for product links are not shown, and URL strings are handled as user-supplied text).

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 0.70). The skill explicitly instructs the agent to "configure [AK/SK] in the system environment variables" without requiring manual terminal operations and to run pip install commands, which ask the agent to modify the host environment and install packages (i.e., change system state) automatically.