grpc-streaming-test-author
Pass
Audited by Gen Agent Trust Hub on Aug 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is a developer-focused authoring tool that provides patterns and skeletons for gRPC testing without performing malicious actions.- [COMMAND_EXECUTION]: The skill instructs the agent to generate file systems and code skeletons for test directories.- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface through the ingestion of external proto files to produce test code.\n
- Ingestion points: The skill reads and classifies user-provided
.protofiles.\n - Boundary markers: Absent.\n
- Capability inventory: Generates directory structures and source code files for Go, Python, Java, and Node.js.\n
- Sanitization: No explicit sanitization of input proto definitions is described.
Audit Metadata