volt-recon
Pass
Audited by Gen Agent Trust Hub on Jul 1, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it is designed to ingest and process untrusted data from firmware project files.\n
- Ingestion points: Reads files such as platformio.ini, sdkconfig, prj.conf, west.yml, and linker scripts to inventory the system (SKILL.md).\n
- Boundary markers: Absent. There are no instructions to use delimiters or ignore embedded instructions within the processed data.\n
- Capability inventory: Utilizes Bash for environment detection and command-line reconnaissance, and the Read tool for file inspection (SKILL.md).\n
- Sanitization: Absent. The instructions do not specify any validation, filtering, or escaping of the content read from external files before the agent processes it.
Audit Metadata