qemu-peripheral-modeling
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local validation script
scripts/check-framework-decision.shand uses git commands to manage workspace settings. It also references an external toolgates.shfor source validation.\n- [INDIRECT_PROMPT_INJECTION]: The skill workflow involves processing potentially untrusted data from hardware datasheets and drivers to extract register contracts.\n - Ingestion points: External hardware datasheets, SDK drivers, firmware traces, and the
register-semantics.irfile.\n - Boundary markers: No specific delimiters or "ignore previous instruction" markers are defined for the ingestion of raw documentation.\n
- Capability inventory: Writing to the local file system, executing shell scripts, and modifying git configurations.\n
- Sanitization: Validation depends on the agent cross-referencing information against official QEMU documentation and cited sources.
Audit Metadata