distributed-tracing
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches the Jaeger Operator deployment manifest directly from the official Jaeger Tracing repository on GitHub during the Kubernetes setup process.
- [COMMAND_EXECUTION]: Instructs the agent to execute shell commands using
kubectlanddocker-composeto deploy and manage observability infrastructure components. - [INDIRECT_PROMPT_INJECTION]:
- Ingestion points: The skill instruments applications to ingest and propagate HTTP headers such as
traceparentandtracestate, as well as database operation metadata (SKILL.md). - Boundary markers: No explicit delimiters are suggested for handling untrusted metadata within spans.
- Capability inventory: The skill utilizes container orchestration and application-level instrumentation to process request flows (SKILL.md).
- Sanitization: No specific sanitization logic is provided for external context headers before they are processed by the tracing provider.
Audit Metadata