openxiangshan/xiangshanlab/riscv-security-hc-spec
Claude Code and agent skill by openxiangshan/xiangshanlab
- community
Checking that the SKILL.md file is still in the repository.
Look up RISC-V Security Horizontal Committee related specifications, including ratified and unratified/development specs. Activate for questions about RISC-V security specifications, memory isolation, memory encryption or confidential computing, I/O isolation, secure interrupts, trusted debug, and control-flow integrity including Zicfilp and Zicfiss.
Install
npx vskill@latest install openxiangshan/xiangshanlab/riscv-security-hc-specSKILL.md
RISC-V Security HC Specification Lookup
Rule
Do not answer RISC-V Security HC specification-status or source-link questions from memory. First check the bundled specification index and, for current status, verify against the official sources listed there.
Primary Reference
Read references/security-hc-specifications.md when the user asks about:
- memory isolation: PMP, Smepmp, SPMP, Smmtt, Worlds, Smpmpmt
- memory encryption or confidential computing: Security Model, CoVE/AP-TEE, HAC, crypto
- I/O isolation: IOMMU, IOPMP, CoVE with I/O
- secure interrupts: AIA, PLIC, CLIC, NMI/double-trap related privileged extensions
- trusted debug: Debug, external debug security, trigger delegation
- control-flow integrity: Zicfilp, Zicfiss, Smcfilp, Smcfiss, shadow stacks
Status Sources
- Ratified specs:
https://riscv.org/specifications/ratified/and the official RISC-V docs library. - Development specs:
https://riscv.org/specifications/-> "VIEW DEVELOPMENT SPECS", backed byhttps://riscv.github.io/adm-spec-dashboard/latest.csv. - If GitHub access is blocked in this environment, run network commands through
bosc-ipv6, for example:
``bash bosc-ipv6 curl -L https://riscv.github.io/adm-spec-dashboard/latest.csv ``
Answering Guidance
When answering, report:
- specification name and extension names where applicable;
- status: Ratified, Development, Stabilization, Freeze, Ratification-Ready, or Planning;
- whether it is ISA, NON-ISA, or both;
- official source link;
- the security category.
If a requested category has no direct public RISC-V spec entry, say so and name the closest related specs instead of inventing one.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingtools/specification-analyzer/riscv-security-hc-spec/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/openxiangshan/xiangshanlab/riscv-security-hc-spec)