loki
Pass
Audited by Gen Agent Trust Hub on Mar 21, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references official Loki documentation and source code on grafana.com and github.com/grafana. These are well-known technology services and are used here for legitimate technical reference.
- [COMMAND_EXECUTION]: Uses curl for health checks and LogQL query testing against a user-defined Loki instance ($LOKI) in SKILL.md. It also uses ripgrep (rg) in SKILL.md for searching local reference documents.
- [PROMPT_INJECTION]: The skill guides the processing of log data which may contain untrusted content. Evidence chain: 1. Ingestion points: Log stream ingestion pipelines (SKILL.md). 2. Boundary markers: Recommendations for tenant-aware authorization are included (SKILL.md). 3. Capability inventory: curl for API interaction (SKILL.md). 4. Sanitization: Recommends redacting sensitive fields prior to ingestion (SKILL.md).
Audit Metadata