qemu-firmware-linux-boot
Pass
Audited by Gen Agent Trust Hub on Jun 18, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill defines a process for capturing and analyzing guest serial logs, which constitutes a surface for indirect prompt injection.
- Ingestion points: Guest serial output is captured and summarized in evidence.md as part of the debugging workflow in SKILL.md.
- Boundary markers: The instructions do not specify the use of delimiters or instructions to ignore embedded content when processing log data.
- Capability inventory: The skill references multiple orchestration tools (qemu-boot-run, qemu-debug) to manage the guest lifecycle and debugging state.
- Sanitization: No validation or escaping of the guest console output is mentioned prior to the agent's summary and analysis.
- [NO_CODE]: The skill consists entirely of markdown instructions and YAML configuration files. There are no executable scripts (such as Python or Shell) or binaries included, which limits the risk of direct code execution or local persistence.
Audit Metadata