stm32-development

Pass

Audited by Gen Agent Trust Hub on Oct 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data which could contain malicious instructions.
  • Ingestion points: User project files such as CMakeLists.txt, Makefile, .ioc files, and linker scripts (identified in SKILL.md and references/workflow.md).
  • Boundary markers: None specified in the instructions to delimit untrusted project content.
  • Capability inventory: The skill utilizes build systems (CMake, Make, PlatformIO) and diagnostic tools (probe-debugging, fault-forensics) which can execute shell commands or modify the environment.
  • Sanitization: No explicit sanitization or validation of project file content is mentioned before processing.
  • [EXTERNAL_DOWNLOADS]: The skill references official resources and package versions from established providers.
  • Evidence: Mentions PlatformIO platform ststm32@19.5.0, which is a standard package for the PlatformIO ecosystem.
  • Evidence: Links to official STMicroelectronics documentation (st.com) and their public GitHub repository (github.com/STMicroelectronics/STM32CubeF4). These are well-known services and organizations within the embedded development domain.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 15, 2026, 12:31 PM