wiring-doc
Pass
Audited by Gen Agent Trust Hub on Jun 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted data from local project files. \n
- Ingestion points: The skill reads various project files including
main/*.c,main/*.h,main/CMakeLists.txt,sdkconfig.defaults,justfile,README.md,CLAUDE.md, andKconfig.projbuild. \n - Boundary markers: There are no explicit delimiters or instructions provided to the agent to isolate the ingested file content from its main instructions. \n
- Capability inventory: The skill utilizes
Write,Edit, andAgenttools, which could potentially be misused if the agent follows malicious instructions embedded within the source files. \n - Sanitization: No explicit sanitization, filtering, or validation is performed on the content of the files before processing.
Audit Metadata