xv6-riscv-expert
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions provide expert domain knowledge for xv6-riscv development without any malicious injection or exfiltration patterns. All external references target official educational repositories (MIT PDOS, SNU CSL) or the author's own public project assets.- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze user-provided kernel code and debug logs. While this presents a standard attack surface for indirect prompt injection, the skill includes structured workflows and specific domain assumptions (e.g., ANSI C, Sv39 page tables) that constrain agent behavior to legitimate development tasks.- [COMMAND_EXECUTION]: The README provides standard installation and environment setup commands (such as
npx,git, andapt) for the user to execute manually. These are routine for setting up a RISC-V development toolchain and do not represent automated or hidden execution by the agent.
Audit Metadata