kubesense-traces
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides instructions for interacting with the KubeSense MCP traces module. It includes guidance on field mapping, unit conversion for duration values, and diagnostic workflows for distributed tracing.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external telemetry data (traces and spans). This creates a potential surface for indirect prompt injection if malicious data is embedded in span attributes, although the risk is minimal given the structured nature of the data and the absence of high-risk capabilities. 1. Ingestion points: Data returned by search-traces and get-distributed-trace in SKILL.md. 2. Boundary markers: None specified. 3. Capability inventory: Limited to structured data querying and analysis via predefined MCP tools; no command execution or file system access is present. 4. Sanitization: No explicit sanitization or validation of the trace content is described.
Audit Metadata