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, and CMakeLists.txt from 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, and Glob tools 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
Risk Level
SAFE
Analyzed
Jun 20, 2026, 08:45 AM
Security Audit — agent-trust-hub — wifi-sta-setup