openstack-swift

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt contains explicit examples that embed secrets verbatim in commands (e.g., Temp-URL key shown as "mysecretkey", swift tempurl usage, and placeholders for AWS/EC2 access & secret keys) which would require the LLM to handle or emit secret values directly in outputs.

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

• Attempt to modify system services in skill instructions detected (high risk: 1.00). The prompt instructs the agent/operator to perform destructive, system-level actions (parted, mkfs.xfs, xfs_admin, xfs_repair, mounting block devices, ring rebalances and kolla-ansible reconfigure) that require root privileges and modify the host's storage and configuration.