k8s-blast-radius
Pass
Audited by Gen Agent Trust Hub on Apr 30, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized network operations were detected in the skill instructions.
- [NO_CODE]: The skill does not distribute any executable scripts or binary files, significantly reducing the attack surface for remote code execution.
- [SAFE]: The referenced tools (k8s-blast-radius, apm-health-summary, apm-service-dependencies, ml-anomalies) are diagnostic in nature and consistent with the author's (elastic) observability ecosystem.
- [PROMPT_INJECTION]: Analysis of indirect prompt injection surface.
- Ingestion points: Processes telemetry data from Kubernetes (kubeletstats) and Elastic APM service health signals.
- Boundary markers: Not explicitly defined in the instruction set.
- Capability inventory: Limited to read-only diagnostic tool invocations for impact assessment and dependency mapping.
- Sanitization: Not explicitly defined; relies on validation by the underlying telemetry backends.
Audit Metadata