gitops-status
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external, untrusted data which creates a vulnerability surface for indirect prompt injection.
- Ingestion points: The skill retrieves application logs (
gitops_pod_log), event data (gitops_app_event), and resource trees (gitops_app_resource_tree) from external Kubernetes and GitOps environments as seen in the MCP tool calls inSKILL.md. - Boundary markers: The instructions lack explicit delimiters or warnings to the agent to disregard instructions that might be contained within the retrieved logs or event descriptions.
- Capability inventory: The agent possesses the capability to perform state-changing actions, such as triggering application synchronizations using the
harness_executetool. - Sanitization: There are no defined mechanisms for sanitizing, filtering, or validating the content of the logs or events before they are processed by the agent.
Audit Metadata