lov-anti-wechat-ai-check
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses a local Python script (
analyze.py) to perform text analysis. The script is invoked with specific arguments for input processing and only uses the Python standard library. - [REMOTE_CODE_EXECUTION]: The skill explicitly states it has no external dependencies and relies solely on the Python standard library. No patterns of downloading and executing remote code were found.
- [DATA_EXFILTRATION]: No network operations or data transmission patterns (e.g., curl, wget, requests) were found in the provided code. All analysis is performed locally.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided text for analysis and rewriting.
- Ingestion points: The
analyze.pyscript reads user-provided files or strings via the--inputor--textflags. - Boundary markers: The skill relies on the script's output report to provide context to the agent, though explicit delimiters for the raw user text are not strictly enforced in the script output.
- Capability inventory: The skill can read local files and perform text transformations.
- Sanitization: The script performs regex-based pattern matching and statistical calculations, which effectively treats the input as raw data rather than instructions during the initial analysis phase.
Audit Metadata