wifi-sta-setup
Pass
Audited by Gen Agent Trust Hub on Jun 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it reads and acts upon untrusted data from the local project files without using boundary markers or sanitization to distinguish between data and potential instructions.\n
- Ingestion points: Reads project files including
main.c,wifi_manager.c,sdkconfig.defaults, andCMakeLists.txtfrom user-specified paths.\n - Boundary markers: None identified in the skill instructions to separate project file content from agent instructions.\n
- Capability inventory: The skill uses
Read,Write,Edit,Grep, andGlobtools to analyze and transform source code and configuration files.\n - Sanitization: No explicit sanitization or validation of the ingested code content is performed before processing.
Audit Metadata