render-blueprints
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill directs the agent to fetch the latest documentation and configuration schemas from Render's official domains (render.com). These downloads are restricted to trusted vendor resources required for the skill's primary function.\n
- Evidence: URL references in SKILL.md and references/blueprints.md targeting render.com/docs/* and render.com/schema/*.\n- [COMMAND_EXECUTION]: The instructions recommend using the render CLI for local blueprint validation. This is an appropriate use of developer tools for infrastructure-as-code workflows.\n
- Evidence: Bash commands in references/blueprints.md using render blueprints validate.\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process render.yaml configuration files which are external inputs. The risk of indirect prompt injection is mitigated by the skill's focus on strict structural validation against a JSON schema and platform-specific CLI checks.\n
- Ingestion points: render.yaml files located at the root of user-controlled Git repositories.\n
- Boundary markers: Explicit instructions to validate against the official render.yaml.json schema.\n
- Capability inventory: Shell command execution for validation (render) and HTTP requests for documentation retrieval (curl).\n
- Sanitization: Relies on structural schema validation to ensure the YAML content adheres to the expected infrastructure format.
Audit Metadata