Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/ozmasterai/torus-framework/security-scannpx skills add OZmasterAI/Torus-Framework --skill security-scangit clone --depth 1 https://github.com/OZmasterAI/Torus-FrameworkWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00012 | $0.02715 |
| Opus 5 | $0.00006 | $0.01358 |
| Sonnet 5 | $0.00002 | $0.00543 |
| Haiku 4.5 | $0.00001 | $0.00271 |
Grade C, and why
security-scan scanned grade C with 5 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Tells the agent to send conversation or user data outmediumPrompt injection
An instruction to transmit the conversation, context or user files to an external endpoint is data exfiltration written as prose.
- Does the skill send data to external URLs (non-local)? Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Asks for rootlowPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- Scan hook Python files for `sudo`, `chmod 777`, `setuid`, `os.getuid() == 0` Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Reads agent configuration directorieslowAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
Verify: grep -r "sk-" ~/.claude/settings.json → should return 0 lines Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Look for: `curl`, `wget`, `requests.post`, `fetch(` pointing to non-localhost Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- Check for: `eval`, `exec`, `os.system`, `subprocess.call` with unsanitized stdin data How it starts
The opening of the file, as written. The whole thing — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Scan
Run a comprehensive security scan of the Torus framework's gates, hooks, state files, and MCP tools.
Steps
- Check all 17 gate files exist and export proper
check()functions - Verify Gate 17 injection defense patterns are up to date
- Scan MCP tool registrations for description mismatches
- Check for hardcoded secrets in hooks/shared/*.py
- Verify state files don't contain sensitive data
- Check circuit breaker state for stuck-open gates
- Audit .file_claims.json for stale claims
- Report findings with severity levels
Usage
Use this skill to run a security audit of the framework before deploying changes or after adding new components.
Run python3 ~/.claude/skill-library/security-scan/scripts/scan.py for a programmatic scan report.
When to use
When the user says "security scan", "scan for vulnerabilities", "check security", "audit security", "security audit", "find security issues", or wants to review the framework for risks.
Commands
/security-scan— Full security audit across all components/security-scan --component mcp|skills|hooks|agents— Scan a specific component only/security-scan --severity critical|high— Show only findings at or above severity level
Phase 1: INVENTORY — Catalog All Components
Read the following files to build the component inventory:
MCP Servers — from settings.json:
~/.claude/settings.json
Extract the mcpServers block. For each server record:
- Name, command, args, env vars (flag any with secrets/tokens in env)
- Transport type (stdio vs sse vs http)
Skills — glob all SKILL.md files:
~/.claude/skill-library/*/SKILL.md
For each skill record: name, trigger phrases, what commands it runs.
Hooks — from settings.json:
~/.claude/settings.json → hooks block
For each hook record: event type, matcher, command string.
Also read gate files:
~/.claude/hooks/gates/gate_*.py (glob)
Agents — glob all agent definitions:
~/.claude/agents/*.md
For each agent record: name, tools list, any capability overrides.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 290 lines · 12 tokens per session scan C d73a23580a8b
security-scan is a skill published in the GitHub repository OZmasterAI/Torus-Framework (5 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 12 tokens to every session and 2,715 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 5 findings (tells the agent to send conversation or user data out, asks for root, reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.