anth-observability
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides standardized implementation examples for structured logging and Prometheus-based metrics to track AI latency, cost, and usage.
- [SAFE]: It emphasizes security best practices by instructing the agent to redact sensitive data, including API keys, user identifiers, and the actual text of prompts and responses, from all telemetry outputs.
- [SAFE]: All referenced external resources are official domains for well-known and trusted services (Anthropic documentation and status pages).
- [SAFE]: The risk of indirect prompt injection is addressed by design; instructions explicitly command the exclusion of content blocks and the focus on non-executable metadata for monitoring purposes.
Audit Metadata