byted-escloud

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

• Third-party content exposure detected (high risk: 0.90). The skill's data-plane workflows (DATA_PLANE.md, SKILL.md, and README) require the agent to run scripts/data.py against arbitrary user-supplied endpoints (via --endpoint or ESCLOUD_ENDPOINT) and to read and act on the cluster responses, which are untrusted third‑party content that can materially influence subsequent tool use and decisions.