configure-notifications

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly asks to collect platform secrets (e.g., "Telegram
• bot token + chat id", optional headers) and instructs writing them directly into the config via shell/jq commands, which requires the agent to handle and embed secret values verbatim.

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

• Third-party content exposure detected (medium risk: 0.30). In “configure-notifications” required workflow (Step 4/4b), the operator-provided free text fields like the “URL”, “headers”, “instruction template”, and “command template” are written into a config that can later be dispatched via OpenClaw/clawdbot agent to external targets.