dokploy

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

• Third-party content exposure detected (high risk: 0.80). This skill's "Update Check" step explicitly fetches and parses the public URL https://raw.githubusercontent.com/abpai/skills/main/versions.json and uses that remote data to decide whether to prompt and run an update (potentially executing commands), so it ingests untrusted third‑party content that can influence agent actions.