helm
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses standard Helm dependency management to fetch subcharts from external repositories.
- Evidence: Mentions
helm dependency buildandhelm dependency updateto resolve requirements from sources such as OCI registries (e.g.,oci://registry.example.com/charts). These are standard operations for the tool's primary purpose. - [INDIRECT_PROMPT_INJECTION]: The agent is instructed to process external data such as Kubernetes logs and resource status tables to assist in debugging.
- Ingestion points: Processes output from
helm upgradeerror banners,kubectl logsfrom hook pods, and Kubernetes resource tables. - Boundary markers: The skill does not explicitly define markers but uses the standard technical context of CLI tool output.
- Capability inventory: Access to
helmandkubectlcommands for cluster management and debugging. - Sanitization: Relies on the user to review command output and specifically warns against automated resource deletion via post-renderers.
Audit Metadata