qemu-linux-boot
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to capture and analyze the full console log from QEMU. This creates an attack surface where a malicious guest image or bootloader could emit instructions designed to influence the agent's behavior during log interpretation.
- Ingestion points: Console log capture described in SKILL.md.
- Boundary markers: Absent; the skill does not specify delimiters for log content.
- Capability inventory: File system access, shell command execution (QEMU), and audit logging.
- Sanitization: Absent; no instructions for filtering or escaping guest output are provided.
- [COMMAND_EXECUTION]: The workflow requires the agent to construct and execute QEMU commands involving system-level parameters like kernel images, drives, and network configurations. This is a functional requirement of the skill but involves powerful system interactions.
Audit Metadata