create-environment
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided inputs to generate environment configurations. While this represents a potential surface for injection, the risk is low due to the structured nature of the YAML output and the specific API-driven tool calls.
- Ingestion points: Environment identifiers, names, variables, and project/org IDs (SKILL.md).
- Boundary markers: Data is structured within YAML code blocks.
- Capability inventory: Restricted to Harness environment management tools (harness_create, harness_list, harness_update).
- Sanitization: The skill relies on the structured YAML format and platform-side validation of the resource payload.
- [CREDENTIALS_UNSAFE]: The skill uses best-practice secret management techniques by demonstrating the use of secret references (e.g.,
<+secrets.getValue("staging_db_password")>) rather than hardcoding credentials.
Audit Metadata