osmo-deploy
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local shell scripts (
deploy-osmo.sh,deploy-osmo-single-plane.sh) and leverages standard system tools includinghelm,kubectl,terraform,jq, and cloud provider CLIs (az,aws) to perform cluster provisioning and deployment tasks.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied configuration data, such as region names, resource IDs, and GPU counts, and uses them to parameterize deployment commands. This constitutes an attack surface for indirect prompt injection.\n - Ingestion points: User inputs for deployment settings (region, GPU count, storage backend) described in
SKILL.md.\n - Boundary markers: The skill does not explicitly mention markers or delimiters for untrusted data.\n
- Capability inventory: The skill possesses extensive capabilities including file system modification (writing Terraform state), network access (via cloud CLIs), and deployment management (Helm/kubectl) as detailed in
SKILL.md.\n - Sanitization: No explicit sanitization or validation logic is provided in the instruction files.
Audit Metadata