Kesekit Check
cdppcorp/KESE-KIT
Run a pre-deployment security compliance checklist based on KISA guidelines.
Audit raytsystem changes for prompt injection, provenance bypass, path/symlink/hardlink escape, secret leakage, stale fencing, partial promotion, unsafe parsing, and unapproved side effects.
Install Raytsystem Security Review
$ npx skills add romarayt/raytsystem-public-os --skill raytsystem-security-review -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install romarayt/raytsystem-public-os raytsystem-security-review --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/romarayt/raytsystem-public-os.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/raytsystem-security-review .claude/skills/raytsystem-security-review && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "raytsystem-security-review" agent skill from https://github.com/romarayt/raytsystem-public-os/tree/main/skills/raytsystem-security-review into .claude/skills/raytsystem-security-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "raytsystem-security-review", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/romarayt/raytsystem-public-os/tree/main/skills/raytsystem-security-reviewType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add romarayt/raytsystem-public-os --skill raytsystem-security-review -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install romarayt/raytsystem-public-os raytsystem-security-review --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/romarayt/raytsystem-public-os.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/raytsystem-security-review .agents/skills/raytsystem-security-review && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "raytsystem-security-review" agent skill from https://github.com/romarayt/raytsystem-public-os/tree/main/skills/raytsystem-security-review into .agents/skills/raytsystem-security-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "raytsystem-security-review", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add romarayt/raytsystem-public-os --skill raytsystem-security-review -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install romarayt/raytsystem-public-os raytsystem-security-review --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/romarayt/raytsystem-public-os.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/raytsystem-security-review .cursor/skills/raytsystem-security-review && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "raytsystem-security-review" agent skill from https://github.com/romarayt/raytsystem-public-os/tree/main/skills/raytsystem-security-review into .cursor/skills/raytsystem-security-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "raytsystem-security-review", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/romarayt/raytsystem-public-os.git --path skills/raytsystem-security-review--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add romarayt/raytsystem-public-os --skill raytsystem-security-review -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install romarayt/raytsystem-public-os raytsystem-security-review --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/romarayt/raytsystem-public-os.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/raytsystem-security-review .gemini/skills/raytsystem-security-review && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "raytsystem-security-review" agent skill from https://github.com/romarayt/raytsystem-public-os/tree/main/skills/raytsystem-security-review into .gemini/skills/raytsystem-security-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "raytsystem-security-review", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install romarayt/raytsystem-public-os raytsystem-security-reviewInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add romarayt/raytsystem-public-os --skill raytsystem-security-review -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/romarayt/raytsystem-public-os.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/raytsystem-security-review .github/skills/raytsystem-security-review && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "raytsystem-security-review" agent skill from https://github.com/romarayt/raytsystem-public-os/tree/main/skills/raytsystem-security-review into .github/skills/raytsystem-security-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "raytsystem-security-review", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add romarayt/raytsystem-public-os --skill raytsystem-security-review -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install romarayt/raytsystem-public-os raytsystem-security-review --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/romarayt/raytsystem-public-os.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/raytsystem-security-review .opencode/skills/raytsystem-security-review && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "raytsystem-security-review" agent skill from https://github.com/romarayt/raytsystem-public-os/tree/main/skills/raytsystem-security-review into .opencode/skills/raytsystem-security-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "raytsystem-security-review", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
raytsystem-security-review- GitHub stars
- 149
- Token cost
- ~572 tokens
- SKILL.md length
- 218 words
- Files
- 2
- Skills in repo
- 12
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Audit raytsystem changes for prompt injection, provenance bypass, path/symlink/hardlink escape, secret leakage, stale fencing, partial promotion, unsafe parsing, and unapproved side effects.
- Works in 3 steps: Run uv run raytsystem agent preflight… → Run agent subagent-check before… → Snapshot declared canonical/external…
- SECURITY REVIEW
- SKILL.md covers Inputs and outputs, Write scope, Preflight and Workflow, plus 3 more sections
- Calls uv
What it does
Raytsystem Security Review is an agent skill from romarayt/raytsystem-public-os. Audit raytsystem changes for prompt injection, provenance bypass, path/symlink/hardlink escape, secret leakage, stale fencing, partial promotion, unsafe parsing, and unapproved side effects. Use for SECURITY REVIEW, adversarial testing, recovery review, or approval-boundary validation; remain independent and read-only.
Its SKILL.md is about 570 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).
It sits in Security, covering Security review and Prompt injection and agent security. The repository describes itself as: Local-first agent workspace for knowledge, tasks, documents and verifiable workflows · Локальная агентная система для знаний, задач и проверяемых процессов · t.me/romarayt. The licence is Apache-2.0.
When your agent uses it
- SECURITY REVIEW
- Adversarial testing
- Recovery review
- Approval-boundary validation
Example prompts
- “/raytsystem-security-review”
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- Run uv run raytsystem agent preflight --skill raytsystem-security-review --write --json locally.
- Run agent subagent-check before delegation; hosted review receives only safe excerpts.
- Snapshot declared canonical/external state and identify every write/egress boundary.
What it can do on your machine
Read from SKILL.md and the folder at commit b5ac705. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
uv
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use uv, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Raytsystem Security Review loads about 572 tokens when it runs. Until then it costs about 87 tokens; SKILL.md has 218 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from romarayt/raytsystem-public-os at commit b5ac705, republished under its Apache-2.0 licence (© romarayt). 218 words, ~572 tokens.
Download SKILL.mdSave it as
.claude/skills/raytsystem-security-review/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- raytsystem-security-review
- description
- Audit raytsystem changes for prompt injection, provenance bypass, path/symlink/hardlink escape, secret leakage, stale fencing, partial promotion, unsafe parsing, and unapproved side effects. Use for SECURITY REVIEW, adversarial testing, recovery review, or approval-boundary validation; remain independent and read-only.
raytsystem Security Review
Inputs and outputs
- Accept one bounded change/run plus threat model and declared permissions.
- Return confirmed or unproven Critical/High findings with repro, violated invariant, and minimal regression test/fix.
Write scope
- Keep review read-only; run only non-mutating diagnostics or isolated synthetic tests.
- Never read secrets without scoped necessity, disclose values, promote, publish, or modify external systems.
Preflight
- Run
uv run raytsystem agent preflight --skill raytsystem-security-review --write --jsonlocally. - Run
agent subagent-checkbefore delegation; hosted review receives only safe excerpts. - Snapshot declared canonical/external state and identify every write/egress boundary.
Workflow
- Trace untrusted input through Fetcher/Extractor/proposal/validation/promotion/query/save paths.
- Test raw/hash/citation closure, generation races, lease fencing, WAL/pointer crash windows, and idempotency.
- Test SQL/FTS injection, resource limits, archive/parser containment, symlink/hardlink/no-follow paths, and secret redaction.
- Verify zero unapproved process/network/outbox/Git/external action.
Validation
- Require a regression test for every confirmed Critical/High issue.
- Re-run scoped and full gates after fixes; never accept skipped required tests.
- Exercise evals
m3-security-review-goldenandm3-security-review-adversarial.
Recovery
- Preserve failed staging and machine-readable reports; retry only classified transient failures.
- On quota/tool loss, list exact reviewed surfaces and remaining adversarial cases.
Stop and approval conditions
- Stop on secret/PII exposure, unsafe external destination, real promotion, destructive action, or missing authority.
- Do not downgrade a confirmed issue because exploitation is inconvenient; fail closed and request the narrow required approval.
© romarayt, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file in skills/raytsystem-security-review of romarayt/raytsystem-public-os.
- SKILL.md
- agents/openai.yaml
Open the folder on GitHubat commit b5ac705
Compare with similar skills
Raytsystem Security Review next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Raytsystem Security Review this skillromarayt/raytsystem-public-os | 149 | — | ~572 | Automated safety check: Pass | Apache-2.0 | |
| Kesekit Checkcdppcorp/KESE-KIT | 360 | — | ~1.3k | Automated safety check: Pass | MIT | |
| Agentic GitHub Actions Auditortrailofbits/skills | 7.5k | 6 repos | ~5.4k | Automated safety check: Notes | CC-BY-SA-4.0 | |
| Agent Security Hardeningaffaan-m/ECC | 276k | — | ~2.7k | Automated safety check: Pass | MIT | |
| Slowmist Agent Securityslowmist/slowmist-agent-security | 508 | — | ~1.4k | Automated safety check: Pass | MIT | |
| AI SAFE2 Secure Build CopilotCyberStrategyInstitute/ai-safe2-framework | 147 | — | ~1.2k | Automated safety check: Pass | Custom licence |
Similar skills
- Official
Agentic GitHub Actions Auditor
trailofbits/skills
Statically audits GitHub Actions workflows that run AI coding agents, tracing attacker-controlled input to agent prompts and flagging unsafe sandbox, trigger and allowlist settings.
Agent Security Hardening
affaan-m/ECC
Security hardening guidance for AI agent frameworks that process untrusted content, invoke tools, write workspace files, manage runtime identifiers, or handle credentials.
Slowmist Agent Security
slowmist/slowmist-agent-security
Comprehensive security review framework for AI agents. An agent skill from slowmist/slowmist-agent-security.
AI SAFE2 Secure Build Copilot
CyberStrategyInstitute/ai-safe2-framework
Applies the AI SAFE2 framework to security reviews, code reviews and compliance mapping for AI agents, RAG pipelines and MCP servers.
Secureclaw
adversa-ai/secureclaw
Security hardening toolkit for OpenClaw. An agent skill from adversa-ai/secureclaw.
More from romarayt/raytsystem-public-os
All 12 skills in this repoGraph
romarayt/raytsystem-public-os
Refresh the raytsystem code graph so it reflects every current file, then confirm it is up to date.
Start
romarayt/raytsystem-public-os
Get raytsystem running in a repository — install it if needed, then launch the interface.
Raytsystem Watch
romarayt/raytsystem-public-os
Inspect video, audio, or supplied transcripts through raytsystem Tool Hub and return evidence-bound speech, visual, OCR, action, transition, and timeline findings.
Raytsystem Ingest
romarayt/raytsystem-public-os
Capture, normalize, propose, validate, and safely promote workspace-local Markdown, text, JSON/JSONL, CSV/TSV, images, or text-bearing PDFs into raytsystem.
Raytsystem Lint
romarayt/raytsystem-public-os
Run deterministic integrity, provenance, projection, link, alias, operation, and secret checks over raytsystem.
Raytsystem Query
romarayt/raytsystem-public-os
Answer questions from the active raytsystem generation using local FTS5 retrieval, canonical record rehydration, verified source spans, and explicit gaps.
Related
Categories
Questions about Raytsystem Security Review
What does Raytsystem Security Review do?
Audit raytsystem changes for prompt injection, provenance bypass, path/symlink/hardlink escape, secret leakage, stale fencing, partial promotion, unsafe parsing, and unapproved side effects. Raytsystem Security Review is an agent skill from romarayt/raytsystem-public-os. Audit raytsystem changes for prompt injection, provenance bypass, path/symlink/hardlink escape, secret leakage, stale fencing, partial promotion, unsafe parsing, and unapproved side effects.
When should I use Raytsystem Security Review?
Raytsystem Security Review fits situations like: SECURITY REVIEW; adversarial testing; recovery review; approval-boundary validation.
How do I install Raytsystem Security Review in Claude Code?
Run `npx skills add romarayt/raytsystem-public-os --skill raytsystem-security-review -a claude-code`. Or copy the skill folder (skills/raytsystem-security-review in romarayt/raytsystem-public-os) into .claude/skills/raytsystem-security-review in your project. Claude Code loads it when a task matches its description.
How do I install Raytsystem Security Review in Codex?
Run `npx skills add romarayt/raytsystem-public-os --skill raytsystem-security-review -a codex`. Or copy the skill folder (skills/raytsystem-security-review in romarayt/raytsystem-public-os) into .agents/skills/raytsystem-security-review in your project. Codex loads it when a task matches its description.
Can I use Raytsystem Security Review in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add romarayt/raytsystem-public-os --skill raytsystem-security-review -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/raytsystem-security-review, .gemini/skills/raytsystem-security-review, .github/skills/raytsystem-security-review and .opencode/skills/raytsystem-security-review in your project.
What does Raytsystem Security Review need to run?
Going by SKILL.md and its folder, Raytsystem Security Review needs the command-line tools its instructions call (uv).
Does Raytsystem Security Review access the network?
SKILL.md contains no URLs. Its commands use uv, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Raytsystem Security Review safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Raytsystem Security Review use?
Raytsystem Security Review is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Raytsystem Security Review use?
About 572 tokens (SKILL.md is roughly 2.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Raytsystem Security Review?
Skills that share tags, products or a category with Raytsystem Security Review: Kesekit Check (cdppcorp/KESE-KIT, 360 stars), Agentic GitHub Actions Auditor (trailofbits/skills, 7.5k stars), Agent Security Hardening (affaan-m/ECC, 276k stars) and Slowmist Agent Security (slowmist/slowmist-agent-security, 508 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Raytsystem Security Review?
romarayt (a GitHub user) maintains it in romarayt/raytsystem-public-os, which has 149 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on October 8, 2026.
Source: romarayt/raytsystem-public-os on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.