esp-idf-setup
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides instructions for installing well-known development tools including
esptool,ruff,pre-commit,clang-format, andcppcheck. These tools are industry standards for embedded systems development and are fetched from official package registries or well-known package managers like pip and Homebrew. - [COMMAND_EXECUTION]: The skill utilizes the
justcommand runner and Docker to manage the build environment, which helps in isolating development activities. It executes benign system discovery commands such aslsto identify serial ports for firmware flashing anddocker --versionto verify the presence of the container runtime. - [INDIRECT_PROMPT_INJECTION]: The skill identifies a surface where user-supplied input (project names) is used to create directories and generate project boilerplate code.
- Ingestion points: The
<name>argument in thenewcommand withinSKILL.mdis ingested directly from user input. - Boundary markers: No specific boundary markers or instructions to ignore instructions embedded in variables are defined in the project templates.
- Capability inventory: The skill possesses the ability to create directories (
mkdir), write files (Write), and execute shell commands (just,docker) as part of the project creation process. - Sanitization: The skill's instructions do not explicitly require validation or sanitization of the project name, representing a potential surface for path traversal if handled improperly by the agent.
Audit Metadata