huawei-cloud-flexus-l-server-scripts-excute

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill contains explicit examples and fallback methods (command-line parameters and interactive prompts) that require embedding AK/SK/security-token values verbatim into commands or prompts, forcing the LLM to handle or output secrets directly.

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

• Third-party content exposure detected (medium risk: 0.30). In do_query_execution/get_script_job_batch, the skill fetches execution-job results from Huawei Cloud COC via the provided execute_uuid and ingests outsider-origin free text from the API’s message (execution log) field, which is then printed to the user.

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

• Attempt to modify system services in skill instructions detected (high risk: 1.00). The skill explicitly instructs creating and executing scripts on target instances as root (default/explicit --execute-user root) and includes examples like installing packages (e.g., Nginx, pip install), which push the agent to perform privileged, state-changing operations on machines.