Cursor Agent
Wraps the cursor-agent CLI tool with seven specialized tools for code interaction including chat, file editing, analysis, repository search, task planning, and command execution with configurable model settings and comprehensive error handling.
0Tools
9Findings
14Stars
—Downloads
Mar 22, 2026Last Scanned
Findings9
5critical
2high
1medium
1low
0informational
criticalK5Auto-Approve / Bypass Confirmation PatternMCP06-excessive-permissionsAML.T0054
Pattern "\-\-(yes|force|no-confirm|no-prompt|assume-yes)\b" matched in source_code: "--force" (at position 2106)
Never auto-approve or bypass human confirmation for operations with side effects. Implement explicit confirmation gates that cannot be programmatically bypassed. If batch/CI mode is needed, require an explicit opt-in flag with audit logging. Required by EU AI Act Art. 14 (human oversight) and OWASP ASI09.
criticalL9CI/CD Secret Exfiltration PatternsMCP07-insecure-configAML.T0057
Pattern "(?:console\.log|print|echo|puts).*(?:process\.env|os\.environ|\$\{?(?:NPM_TOKEN|NODE_AUTH_TOKEN|GITHUB_TOKEN|AWS_ACCESS|DATABASE_URL|ANTHROPIC_API_KEY))" matched in source_code: "echoEnabled = process.env" (at position 6881)
Never print, log, or transmit CI environment variables containing secrets. Use GitHub Actions '::add-mask::' to prevent accidental secret exposure in logs. Audit all third-party Actions for secret access patterns. Use OIDC tokens instead of long-lived secrets where possible. Restrict secret access to specific workflow jobs and steps. Monitor CI logs for base64-encoded strings.
criticalC1Command InjectionMCP03-command-injectionAML.T0054
Pattern "child_process" matched in source_code: "child_process" (at position 438)
Replace exec()/execSync() with execFile() and pass arguments as an array, never as a string. Validate all inputs against an allowlist before use in any shell context. For subprocess.run, always pass a list and shell=False.
criticalJ5Tool Output Poisoning PatternsMCP02-tool-poisoningAML.T0054
Pattern "(return|respond|output).*(?:tool_call|function_call|execute_tool|call_tool|invoke)" matched in source_code: "return await invoke" (at position 15246)
Tool responses MUST NOT contain instruction-like content, file read directives, or social engineering phrases. Error messages should be factual and technical — never suggest actions involving sensitive data access. See CyberArk ATPA research for attack demonstration.
criticalQ13MCP Bridge Package Supply Chain AttackMCP10-supply-chainAML.T0054
Pattern "["']@modelcontextprotocol/sdk["']\s*:\s*["'](?:\^|~|\*|latest)" matched in source_code: ""@modelcontextprotocol/sdk": "^" (at position 16397)
MCP bridge packages (mcp-remote, mcp-proxy, @modelcontextprotocol/sdk, fastmcp) are high-value supply chain targets — CVE-2025-6514 (CVSS 9.6) in mcp-remote affected 437,000+ installs. Always pin exact versions (no ^ or ~ ranges). Use lockfiles (package-lock.json, pnpm-lock.yaml, uv.lock). Never run `npx mcp-remote` without version pinning. Verify package integrity with `npm audit` or `pip-audit` before deployment. Reference: CVE-2025-6514, OWASP ASI04.
highQ15A2A/MCP Protocol Boundary ConfusionMCP06-excessive-permissionsAML.T0054
Pattern "(?:discover|register|advertise).*(?:agent|skill|capability)(?!.*(?:verify|auth|sign|trust))" matched in source_code: "register a suite of cursor-agent" (at position 7254)
Servers bridging A2A and MCP protocols must: (1) sanitize all A2A task metadata before passing to MCP tool inputs, (2) apply MCP content policies to A2A TextPart/FilePart/DataPart content, (3) validate A2A push notifications before they re-enter MCP context, (4) require cryptographic verification for agent discovery and registration (prevent fake agent advertisement — arXiv 2602.19555), (5) maintain separate permission models for A2A and MCP operations — trust in one protocol must not automatically grant trust in the other.
highD1Known CVEs in DependenciesMCP08-dependency-vuln
Dependency "@modelcontextprotocol/sdk@1.17.3" has known CVEs:
Update dependencies to versions that patch known CVEs. Run 'npm audit fix' or 'pip-audit' to identify and resolve vulnerable dependencies.
mediumK17Missing Timeout or Circuit BreakerMCP07-insecure-configAML.T0054
Pattern "(?:exec|execSync|spawn|subprocess\.run|os\.system)\s*\((?!.*(?:timeout|kill|maxBuffer|signal))" matched in source_code: "spawn(" (at position 3057)
Add timeouts to ALL external calls: HTTP requests (30s), database queries (10s), subprocess execution (60s), and MCP tool calls (30s). Implement circuit breakers that open after N consecutive failures (e.g., opossum, cockatiel). Use AbortSignal for cancellable operations. Required by EU AI Act Art. 15 and OWASP ASI08.
lowF4MCP Spec Non-ComplianceMCP07-insecure-config
Server fails MCP spec compliance checks: required:server_name; required:server_version; required:protocol_version; recommended:tool_descriptions; recommended:parameter_descriptions
Follow the MCP specification for server metadata. Include server name, version, and protocol version. Provide descriptions for all tools and parameters.
Tools
No tools exposed by this server.
Security Category Deep Dive
Sub-Category Tree · Remediation Roadmap · Attack Stories · Compliance Overlay · ATLAS Techniques · Maturity Model
Prompt Injection
Prompt & context manipulation attacks
69
Maturity
14
Rules
5
Sub-Categories
1
Gaps
64%
Implemented
56
Tests
1
Stories
100%3 rules
Injection via tool descriptions and parameter fields
GAP-001Prompt Injection Coverage GapMissing detection coverage for emerging prompt injection attack variants not addressed by current rules
100%4 rules
Hidden instructions via external content and tool responses
100%2 rules
Context window saturation and prior-approval exploitation
100%3 rules
Payload hiding via invisible chars, base64, schema fields
50%2 rules1 found
Injection via prompt templates and runtime tool output