helm-release-recovery
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines patterns where untrusted user input, such as release names or namespaces, is interpolated directly into shell commands for execution.
- Ingestion points: User-supplied values for
<release>and<namespace>parameters found in bothSKILL.mdandREFERENCE.md. - Boundary markers: The instructions do not define delimiters or specific "ignore" markers for data retrieved from external tool outputs (like Helm secrets or resource manifests).
- Capability inventory: The skill is configured to use the
Bashtool to perform high-impact cluster operations includinghelm rollback,helm uninstall, andkubectl delete. - Sanitization: The skill lacks explicit instructions for the agent to validate or sanitize these input parameters against shell injection characters.
- [COMMAND_EXECUTION]: The skill is designed to facilitate the execution of powerful administrative commands through the
Bashtool. These operations allow the agent to modify or delete resources within the Kubernetes cluster, which is consistent with the recovery purpose but represents a significant capability level.
Audit Metadata