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 skills add UnboundCompute/security-agent-skills --skill auditing-editor-extension-workspace-trustgit clone --depth 1 https://github.com/UnboundCompute/security-agent-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/unboundcompute/security-agent-skills/auditing-editor-extension-workspace-trust)<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/auditing-editor-extension-workspace-trust"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-editor-extension-workspace-trust/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/auditing-editor-extension-workspace-trust"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-editor-extension-workspace-trust.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00188 | $0.02092 |
| Opus 5 | $0.00094 | $0.01046 |
| Sonnet 5 | $0.00038 | $0.00418 |
| Haiku 4.5 | $0.00019 | $0.00209 |
Grade A, and why
auditing-editor-extension-workspace-trust scanned grade A with 0 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 11d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auditing editor extension workspace trust: what an untrusted repository makes the editor do on open
An editor extension turns dangerous the moment merely opening a cloned repository makes it run code the
repository controls. The threat is not a user choosing to run something; it is a drive-by, a hostile
.vscode/tasks.json, a settings.json that names the compiler binary, an activation event that fires on
folder open and shells out before the user has trusted anything. You audit it by resolving, per risky
action, whether a workspace-trust gate or an explicit user gesture stands between the untrusted repo and
the execution sink. The discipline is separating an action that genuinely fires on open from one that
needs a deliberate click, and a value read from workspace settings from one read from user or global
settings a repo cannot set.
When to use
- You are reviewing an editor or IDE extension manifest, its activation events, and its trust capability.
- The extension reads workspace configuration, runs tasks, or resolves a tool or binary path from a repo.
- You want to know whether opening a hostile repository executes code before the user trusts it.
Scope check
Audit only extensions you own or are authorized to assess, and open a crafted hostile workspace only on a machine and account in scope, an auto-executed task runs real code on your host. Adjudicate on the manifest and the handler. If you can't name the authorization, stop.
The loop
-
Resolve the trust capability and activation events first. Read the manifest for the untrusted-workspace capability (does it declare it unsupported, limited, or fully supported) and for the activation events. An event like folder-open, a startup-finished event, or a workspace-contains glob makes the extension activate on any repo; a narrow language or command event does not. The gate and the activation trigger decide whether a sink is drive-by reachable, so settle both before flagging.
-
Check auto-run tasks and debug launches. Look for the extension running a task, a command, or a debug preLaunchTask on activation or on open, before or without a trust gate. A task defined in the workspace that fires automatically is repo-controlled code executing on open.
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.
- 11d ago First seen · 136 lines · 188 tokens per session scan A 9bc580edac88
auditing-editor-extension-workspace-trust is a skill published in the GitHub repository UnboundCompute/security-agent-skills (5 stars, last pushed 2d ago), licensed MIT. It adds 188 tokens to every session and 2,092 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
prodcheck-review
Review this codebase against the prodcheck pre-production checklists — security, performance, scale, integrations and post-launch readiness. Use when asked to check whether a project is ready to ship, to audit an area before launch, or to work through a specific checklist. Produces evidence with file:line citations…
integrate-arcjet-guard-genkit
Integrate Arcjet security into a Genkit JS agent using @arcjet/guard — wrap ai.defineTool, put guardMiddleware on generate({ use }) for unwrapped / MCP / filesystem tools, and read a caller-owned id from generate({ context }). Use when asked to add Arcjet to genkit, rate limit its tools, screen inbound messages, or…
integrate-arcjet-guard-langgraph
Integrate Arcjet security into a LangGraph Graph API agent using @arcjet/guard — wrap tool() / StructuredTool, wrap ToolNode for unwrapped MCP tools, and read threadid for correlation. Use when asked to add Arcjet to a LangGraph StateGraph / ToolNode agent, rate limit its tools, screen inbound messages, or block…
integrate-arcjet-guard-tanstack-ai
Integrate Arcjet security into a TanStack AI chat() app using @arcjet/guard — put guardMiddleware first on chat({ middleware }) so onBeforeToolCall gates tools, and read a caller-owned id from chat({ context }). Use when asked to add Arcjet to TanStack AI, rate limit its tools, screen inbound messages, or block prompt…
integrate-arcjet-guard-claude-managed-agents
Integrate Arcjet security into Claude Managed Agents (hosted REST+SSE, beta managed-agents-2026-04-01) using @arcjet/guard — screen user.message / initialevents before sessions.events.send, and gate custom tools on agent.customtooluse. Use when asked to add Arcjet to Claude Managed Agents, rate limit custom tools, or…
swiftui-expert-skill
Write, review, or improve SwiftUI code following best practices for state management, view composition, performance, macOS-specific APIs, and iOS 26+ Liquid Glass adoption. Use when building new SwiftUI features, refactoring existing views, reviewing code quality, or adopting modern SwiftUI patterns.