signoz-creating-alerts

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs the agent to accept and pass type-specific secrets (e.g., Slack webhook URLs or PagerDuty integration keys) as channel configuration when calling signoz:signoz_create_notification_channel, which requires embedding those secret values verbatim in the agent's output/tool payloads.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly requires reading the MCP resources signoz://alert/instructions and signoz://alert/examples at runtime as the source-of-truth for alert JSON schema and query shapes, and those fetched resources directly determine how the agent constructs prompts/configs, so these signoz:// URIs are runtime dependencies that control agent behavior.