k8s-management
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection (LOW): The skill enables the agent to ingest untrusted data by reading Kubernetes pod logs using
kubectl logs. - Ingestion points:
kubectl logsoutput as defined inSKILL.mdworkflows and examples. - Boundary markers: The skill does not provide instructions to the agent to treat log content as data only or to ignore embedded instructions (delimiters are absent).
- Capability inventory: The agent uses the
kubectlCLI. While the skill claims to be read-only, the actual capabilities are determined by the user's local RBAC configuration, which could include destructive actions. - Sanitization: There is no evidence of log sanitization or filtering before the data is presented to the LLM.
Audit Metadata