using-asyncio-python
Pass
Audited by Gen Agent Trust Hub on May 16, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill provides high-quality educational content and a legitimate static analysis utility (
scripts/check_blocking.py) to assist developers with asynchronous Python programming. - [PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection (Category 8) as it ingests untrusted code for its 'Async Review' mode. 1. Ingestion points: User-supplied Python code snippets in the chat interface. 2. Boundary markers: Not explicitly used to isolate user code from instructions. 3. Capability inventory: Includes static analysis, code generation, and file reading via a local script. 4. Sanitization: The skill does not sanitize the content of ingested code before processing. This is categorized as LOW severity representing an inherent vulnerability surface.
- [COMMAND_EXECUTION]: The included script
scripts/check_blocking.pyuses theastmodule for static analysis. It reads the content of local Python files but does not execute them or exfiltrate information, and thus performs its intended function safely.
Audit Metadata