esp-idf
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources that could contain instructions to override agent behavior.
- Ingestion points: The agent reads project files like README, CI configuration, and sdkconfig.defaults in SKILL.md, and fetches metadata from the ESP Component Registry API in component_registry.md.
- Boundary markers: There are no explicit instructions to use delimiters or ignore embedded content within these sources.
- Capability inventory: The skill allows shell execution via idf.py, eim, and esptool, and file writing via idf.py create-project.
- Sanitization: No sanitization or validation procedures are defined for ingested external data.
- [COMMAND_EXECUTION]: The skill uses CLI tools such as idf.py, esptool, and eim to perform builds and hardware operations, which is normal for this developer-oriented use case.
- [EXTERNAL_DOWNLOADS]: The skill downloads components and toolchains from official Espressif infrastructure (components.espressif.com), which is a well-known vendor service for ESP32 development.
Audit Metadata