async-repl-protocol
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill acts as a developer guide for an asynchronous Read-Eval-Print Loop (REPL) environment. It outlines the correct usage of the
awaitkeyword and constraints on code block execution. - [INDIRECT_PROMPT_INJECTION]: The skill documentation references tools that process external data, establishing a potential attack surface for indirect prompt injection during testing operations.
- Ingestion points: Reference to
view_file(path)andask_memory(...)tools inSKILL.md. - Boundary markers: No specific boundary markers or 'ignore' instructions are provided in the guide.
- Capability inventory: The guide describes an 'async REPL harness', which facilitates code execution.
- Sanitization: No sanitization or validation methods are detailed for the tool outputs.
Audit Metadata