observability-engineer
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary focus on telemetry analysis creates an attack surface for indirect prompt injection from untrusted data sources.
- Ingestion points: The agent is instructed to process data from various external sources including logs (ELK, Splunk, Loki), distributed traces (Jaeger, Zipkin), and APM systems as described in the capabilities section.
- Boundary markers: The instructions do not define delimiters or provide specific directives to treat external telemetry data as untrusted or non-executable content.
- Capability inventory: The skill incorporates the use of high-impact automation and infrastructure-as-code tools like Terraform and Ansible for production environment management.
- Sanitization: No explicit requirements for sanitizing or validating telemetry data before it is processed by the agent are present in the skill definition.
Audit Metadata