secrets
Pass
Audited by Gen Agent Trust Hub on Feb 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill describes using standard administrative tools including
kubectl,aws ssm, andtaskfor managing cluster resources and cloud parameters. - [EXTERNAL_DOWNLOADS]: Mentions external Kubernetes controllers and schemas from
mittwaldandexternal-secrets.io, which are widely used open-source projects. - [PROMPT_INJECTION]: The skill is subject to potential indirect prompt injection through external data sources. Ingestion points: Processes data from AWS SSM Parameter Store and Kubernetes resources. Boundary markers: No specific delimiters are defined for isolating external content. Capability inventory: Includes the ability to execute cluster management and cloud provider commands. Sanitization: Relies on the user's infrastructure-as-code validation and standard CLI tool behaviors.
- [DATA_EXFILTRATION]: References sensitive file paths like
~/.kube/<cluster>.yamland~/.secrets/homelab/. These are documented for administrative access and disaster recovery purposes, consistent with the primary skill objective.
Audit Metadata