observability-service-reliability
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill facilitates standard SRE workflows using official vendor-supported tools and documentation. No malicious patterns or unauthorized behaviors were identified. Authored by the platform vendor, it correctly scopes its operations to the 'elastic' CLI tool.
- [INDIRECT_PROMPT_INJECTION]: The skill interacts with external cluster data, creating a potential surface for indirect prompt injection as part of its core functionality. This is a design requirement for the skill's purpose and does not escalate the verdict.
- Ingestion points: The skill retrieves index mappings, field capabilities, and raw metric documents from the target Elasticsearch cluster as described in SKILL.md.
- Boundary markers: The skill does not define specific boundary markers or instructions to isolate data ingested from the cluster from operational instructions.
- Capability inventory: The agent is granted the ability to perform CRUD operations (create, update, delete) on SLOs and alerting rules using the 'elastic' CLI.
- Sanitization: No explicit instructions for sanitizing or validating cluster-sourced metadata are provided in the skill instructions.
Audit Metadata