k8s-launch-kit-shared
Fail
Audited by Gen Agent Trust Hub on Aug 1, 2026
Risk Level: HIGHCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs users and agents to execute an installation script (
scripts/install.sh) usingsudo. This grants the script full administrative access to the underlying host system to perform privileged operations. - [EXTERNAL_DOWNLOADS]: The
l8k preset updatecommand is designed to fetch and update topology presets directly from GitHub. This involves downloading remote content into the execution environment. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it processes untrusted cluster data which is then used to generate Kubernetes manifests.
- Ingestion points: The
l8k discovercommand reads hardware and configuration data from the Kubernetes cluster. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the cluster data are provided.
- Capability inventory: The skill uses the ingested data to drive the
l8k generatecommand, which produces executable Kubernetes YAML manifests. - Sanitization: There is no evidence of sanitization or validation of the cluster-provided data before it is interpolated into the manifest generation process.
Recommendations
- AI detected serious security threats
Audit Metadata