troubleshoot-ssi
Pass
Audited by Gen Agent Trust Hub on Apr 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill installs the
pupCLI tool from the official Datadog Labs Homebrew tap (datadog-labs/pack). This tool is essential for querying Datadog's fleet and trace status. - [COMMAND_EXECUTION]: The skill utilizes
kubectlto interact with Kubernetes resources,dockerfor image building, andpupfor Datadog API interactions. These commands are consistent with the skill's purpose of cluster-level troubleshooting and remediation. - [PROMPT_INJECTION]: The skill identifies an attack surface for indirect prompt injection by ingesting external data during diagnostics.
- Ingestion points: Processes data from
kubectl logs, pod manifests (kubectl get -o yaml), and local application source code files. - Boundary markers: No explicit delimiters or warnings are used for ingested content.
- Capability inventory: The skill has the ability to modify the cluster via
kubectl apply,kubectl rollout restart, and image deployment commands. - Sanitization: No specific sanitization or filtering of external data is performed before processing.
Audit Metadata