qemu-tcg-backend
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes project source code and documentation which are potential vectors for indirect prompt injection.
- Ingestion points: Reads TCG headers and backend implementation files (e.g.,
tcg-target.c.inc) from the local workspace. - Boundary markers: No specific delimiters or safety instructions are provided to separate untrusted file content from agent instructions.
- Capability inventory: The agent is instructed to execute build commands, run tests, and write files to the workspace.
- Sanitization: No input sanitization is specified for the processed source code.
- [COMMAND_EXECUTION]: The skill workflow requires executing shell commands for building the project, running tests, and managing git configurations.
- Evidence: Instructions include running
git rev-parse, project-specific build system commands, and test suites.
Audit Metadata