菜单
Caido proxy integration for HTTP history search, request replay, fuzzing results, sitemap, and security findings via MCP. Use when you need to search proxy traffic, replay requests with modifications, triage fuzzing results, or document findings in Caido.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | caido-proxy |
| description | Caido proxy integration for HTTP history search, request replay, fuzzing results, sitemap, and security findings via MCP. Use when you need to search proxy traffic, replay requests with modifications, triage fuzzing results, or document findings in Caido. |
MCP integration with Caido proxy. Results load into context -- keep queries focused.
If
python3 -c "import caido_sdk_client"succeeds in the current runtime, prefer thecaido-sdkskill instead — direct SDK calls avoid per-tool MCP round-trips and are more efficient. Use this MCP path when the SDK is not importable (its usual state outside the MCP's own env) or Caido is unreachable.
req.host.eq:"example.com" # Exact host match
req.host.cont:"example" # Contains
req.path.cont:"/api/" # Path contains
req.method.eq:"POST" # Exact method
resp.code.eq:200 # Status code
resp.code.gte:400 # Greater than or equal
# Combinators
req.host.eq:"a.com" AND req.method.eq:"POST"
NOT req.path.cont:"/health"
# Security queries
req.header["authorization"].cont:"Bearer"
req.body.cont:"password"
resp.code.gte:500
mcp__caido__list_requests -- search proxy history with HTTPQL
httpql: filter stringlimit: max results (default 20, max 100)mcp__caido__get_request -- full request/response
ids: request ID arrayinclude: ["requestHeaders", "requestBody", "responseHeaders", "responseBody"]mcp__caido__send_request -- send raw HTTP request
raw: full HTTP request texthost: target hostport: target port (default 443)tls: use HTTPS (default true)mcp__caido__list_automate_sessions -- list fuzzing sessions
mcp__caido__get_automate_session -- session details
mcp__caido__get_automate_entry -- fuzzing results with pagination
mcp__caido__create_finding -- document a security finding
requestId: associated request IDtitle: finding titledescription: detailed description1. Search: mcp__caido__list_requests(httpql: 'req.path.cont:"/api/" AND req.method.eq:"GET"', limit: 50)
2. Inspect: mcp__caido__get_request(ids: ["<id>"], include: ["requestHeaders","requestBody","responseHeaders","responseBody"])
3. Replay with modified ID: mcp__caido__send_request(raw: "<modified request>", host: "target.com")
4. Document: mcp__caido__create_finding(requestId: "<id>", title: "IDOR in /api/users/{id}")
1. mcp__caido__list_automate_sessions()
2. mcp__caido__get_automate_session(id: "<session_id>")
3. mcp__caido__get_automate_entry(id: "<entry_id>", limit: 20)
Compare response sizes/codes for anomalies
| Error | Fix |
|---|---|
Invalid token | Run caido-mcp-server login |
Connection refused | Start Caido desktop app |
No such tool | Check capability MCP config |
lsof -i :8080 # Caido running?
which caido-mcp-server # Binary exists?
cat ~/.config/caido-mcp-server/token # Authenticated?
Pre-engagement reconnaissance workflow using HackerOne MCP tools to enumerate program scope, study prior disclosures, and identify high-value targets. Use when starting a new HackerOne program engagement, building an asset inventory, or planning target selection before active testing.
Pre-submission eligibility check for bug bounty findings. Catches ineligible patterns, AI/scanner false positives, and generates impact justification for borderline lows. Use before writing a report or when assessing whether a finding is worth reporting.
Static code analysis for DOM-based vulnerabilities in client-side JavaScript -- source/sink enumeration via grep and AST tools, data flow tracing, sanitization assessment, and framework-specific sink detection. Use when performing pre-commit reviews, auditing large codebases without dynamic execution, or triaging minified code for XSS issues.
Create custom jxscout analyzers (regex, derived, or script-based) and retrigger analysis. Use when the user wants to find specific code patterns across all project files, add new match kinds, or extend jxscout's static analysis capabilities.
Use when the user wants to connect to Jira, Confluence, or Compass — search issues with JQL, read or create issues and pages, link content across products, or set up Atlassian auth. The connector — not security tradecraft.
Use when the user wants to connect to Azure DevOps — query Boards work items with WIQL, read PRs, inspect pipeline runs, create or update work items and wiki pages, or set up ADO auth. The connector — not security tradecraft.