k8s-workload-troubleshooting
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from Kubernetes logs and events, which serves as a potential vector for indirect prompt injection.
- Ingestion points: The skill ingests untrusted data via
kubectl logs,kubectl events, andkubectl describecommands (referenced inSKILL.md,references/crashloop.md,references/probes.md, andreferences/rollouts.md). - Boundary markers: There are no explicit delimiters or boundary markers used when interpolating log or event content into the agent's context.
- Capability inventory: The skill utilizes powerful modification capabilities including
kubectl set image,kubectl set resources,kubectl patch,kubectl rollout undo, andkubectl exec(found inSKILL.mdand reference files). - Sanitization: The skill provides manual sanitization instructions, telling the agent to "Never read Secrets" and "If logs or output contain passwords, tokens or keys, do not repeat them".
- [COMMAND_EXECUTION]: The skill relies on executing
kubectlcommands for investigation and remediation. - The skill uses
kubectl get,describe,logs,events, androlloutfor investigation. - Modification commands like
kubectl set image,patch, androllout undoare explicitly gated behind user approval ("Ask first" pattern), reducing the risk of unauthorized changes.
Audit Metadata