bicep-diagrams
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions require the agent to execute
curlcommands to interact with the Eraser API athttps://app.eraser.io/api/render/elements. This is the intended mechanism for rendering the diagrams and uses an environment variable (ERASER_API_KEY) for authentication. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted user data in the form of Azure Bicep files (
.bicep). - Ingestion points: User-provided Bicep resource declarations, modules, and configurations described in Step 1 of the instructions.
- Boundary markers: The instructions do not specify the use of clear delimiters or "ignore" warnings when parsing the user-provided code.
- Capability inventory: The skill has the capability to execute shell commands via
curland perform network operations to theapp.eraser.iodomain. - Sanitization: There are no explicit sanitization or validation steps mentioned for the Bicep code before it is parsed and converted into Eraser DSL.
Audit Metadata