All Claude Code modshome-dev-lab/workflow-toolbox
wt-secret-guard
Function-hook secret scrubber for prompts, assistant text, tool results, and raw outbound tool inputs
review UI rewrite
wt-secret-guard reaches L2 (writes or runs) and passed claude plugin validate on Claude Code 2.1.302.
- Events hooked: 6
- API methods referenced: 11
- Access from classified calls: L2, writes or runs: runs processes, writes files, reads files, reads env vars, persists state, draws
- Static scan, not a runtime test
Install hint
/plugin install wt-secret-guard --marketplace home-dev-lab/workflow-toolboxFrom the repository's own marketplace. Confirm the plugin name in the repository's README before installing. Mods need Claude Code 2.1.287 or later.
Access
L2 Writes or runsruns processes, writes files, reads files, reads env vars, persists state, drawsValidation
Passed on Claude Code 2.1.302View the source on GitHub Back to the list
What the scan recorded
- Observed events
- Bash calls, Read calls, NotebookRead calls, Write calls, Edit calls, NotebookEdit calls, WebFetch calls, WebSearch calls, Agent calls, Task calls, Grep calls, Glob calls, /"^mcp__"/ calls, /".*"/ calls, every prompt
- Hooks
session.receive, prompt.attachment, tool.call {tool=Bash}, tool.call {tool=Read}, tool.call {tool=NotebookRead}, tool.call {tool=Write}, tool.call {tool=Edit}, tool.call {tool=NotebookEdit}, tool.call {tool=WebFetch}, tool.call {tool=WebSearch}, tool.call {tool=Agent}, tool.call {tool=Task}, tool.call {tool=Grep}, tool.call {tool=Glob}, tool.call {tool=/"^mcp__"/}, tool.call {tool=/".*"/}, turn.step, ui.render {component=AssistantMessage}, prompt.submit- API calls
$.clock.sleep, $.env.get, $.fs.read, $.fs.stat, $.fs.write, $.process.run, $.session.cwd, $.session.id, $.store.get, $.store.set, $.ui.log- Validation on 2.1.302
- Passed
- Scanned revision
12f2f264cdc4- Marketplace passed
- workflow-toolbox
- UI rewrite review
- UI hook source contains control-character strings. Review any values passed to next() as rewritten props.text; the scanner does not trace whether these strings reach that call. plugins/wt-secret-guard/hooks/prompt-storage.js:58, plugins/wt-secret-guard/hooks/reference-runtime.js:128, plugins/wt-secret-guard/hooks/references.js:300, plugins/wt-secret-guard/hooks/references.js:314, plugins/wt-secret-guard/hooks/references.js:331, plugins/wt-secret-guard/hooks/references.js:345
These are the hooks and API calls reported by claude plugin validate. Access levels describe the widest reach of those calls and are not safety ratings. Validation is a static check, not a runtime test, and a passing result does not prove that a mod works or is safe. How the scan works.
More from home-dev-lab/workflow-toolbox
- pilot-guardAuthor, scaffold, and debug multi-agent workflows for Claude Code's Workflow tool: a skills-only plugin plus…
- workflow-toolboxToolbox for Claude Code's Workflow tool: author deterministic multi-agent workflow scripts (workflow-composer…
- wt-deep-searchEXPERIMENTAL. Answers a WebSearch from the local Claude Code doc mirror, context7, Brave or Exa, and adds a d…
- wt-rules-on-demandEXPERIMENTAL. Deliver frontmatter-triggered rules at matching prompts and tool calls.
Badge for your README
Authors can show the latest scan result in their README. Each badge links to this page.
[](https://mods.aidojo.si/mods/home-dev-lab--workflow-toolbox--wt-secret-guard/)
[](https://mods.aidojo.si/mods/home-dev-lab--workflow-toolbox--wt-secret-guard/)