VuNet vuSmartMaps
VuNet vuSmartMaps observability platform with multi-tenant metrics, traces, and logs.
0Tools
14Findings
0Stars
Mar 24, 2026Last Scanned
4 critical · 8 high · 1 medium · 1 low findings detected
Security Category Deep Dive
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
Findings14
4critical
8high
1medium
1low
Critical4
criticalQ13MCP Bridge Package Supply Chain AttackMCP10-supply-chainAML.T0054
Pattern "["']@modelcontextprotocol/sdk["']\s*:\s*["'](?:\^|~|\*|latest)" matched in source_code: ""@modelcontextprotocol/sdk": "^" (at position 18622)
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.
criticalC1Command InjectionMCP03-command-injectionAML.T0054
Pattern "`[^`]+`" matched in source_code: "`Failed to logout:`" (at position 2104)
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.
criticalK14Agent Credential Propagation via Shared StateMCP05-privilege-escalationAML.T0054
Pattern "(process\.env|os\.environ|setenv|putenv).*(?:token|credential|api[_\s-]?key|secret|password)" matched in source_code: "process.env.VUNET_PASSWORD" (at position 1199)
Never write credentials to shared agent state. Use credential vaults (HashiCorp Vault, AWS Secrets Manager) with per-agent scoped access. Implement OAuth token exchange (RFC 8693) for cross-agent authorization. Redact credentials from all agent outputs before writing to shared memory. Required by OWASP ASI03/ASI07 and MAESTRO L7.
criticalC10Prototype PollutionMCP05-privilege-escalation
Pattern "Object\.assign\s*\([^,)]+,\s*(?:req|input|param|args|body|query|data)" matched in source_code: "Object.assign(params, args" (at position 5543)
Sanitize all user-supplied keys before merging into objects. Use Object.create(null) for configuration objects to strip prototype. Validate that keys don't include '__proto__', 'constructor', or 'prototype'. Use structuredClone() for deep copying untrusted data.
High8
highC3Server-Side Request Forgery (SSRF)MCP04-data-exfiltrationAML.T0057
Pattern "\baxios\.(?:get|post|put|delete|patch|head|options|request)\s*\(\s*(?:req|request|input|param|params|args|url|uri|href|link|target|destination|endpoint|host|address|resource|src|source|proxy)" matched in source_code: "axios.post(
url" (at position 3361)
Validate ALL user-supplied URLs before making HTTP requests:
1. Parse the URL and check the hostname against an explicit allowlist of permitted domains.
2. Block requests to RFC 1918 private ranges: 10.0.0.0/8, 172.16.0.0/12, 192.168.0.0/16.
3. Block loopback (127.0.0.0/8), link-local (169.254.0.0/16), and IPv6 equivalents.
4. Block file:// and other non-http(s) protocols explicitly.
5. Disable automatic redirect following, or re-validate each redirect destination.
6. In cloud environments: block requests to IMDS endpoints (169.254.169.254,
metadata.google.internal) at both the application AND network layer.
Example (Node.js): Use the `ssrf-req-filter` package or implement URL validation
against an allowlist before calling fetch/axios/got.
highJ5Tool Output Poisoning PatternsMCP01-prompt-injectionAML.T0054
[AST — J5] Catch block at L154 interpolates error variable "error" into response. If the error originates from attacker-controlled input (e.g., malformed data), the error message becomes an injection vector into the AI's context.
Never include user input or LLM manipulation directives in error messages or tool responses. Use structured error codes.
highK13Unsanitized Tool OutputMCP02-tool-poisoningAML.T0054
Pattern "(?:query|execute|select|find).*(?:return|respond|result|rows|data)(?!.*(?:sanitize|escape|encode|map|filter|select|pick))" matched in source_code: "Query a metric/data" (at position 6165)
Sanitize all external data before including in tool responses. Implement output encoding that neutralizes prompt injection patterns. Truncate excessively long content. Validate structure before passing database results. Apply the principle: treat all external data as untrusted, even in tool outputs. Required by CoSAI MCP-T4.
highK16Unbounded Recursion / Missing Depth LimitsMCP07-insecure-configAML.T0054
Pattern "(invoke|call|execute)[_\s-]?(?:tool|agent|self)(?!.*(?:depth|level|limit|max[_\s-]?(?:depth|recursi|iter|call)|count))" matched in source_code: "CallTool" (at position 209)
Add explicit depth/recursion limits to all recursive operations. Use iterative approaches where possible. Set maximum depth for directory walking (max_depth=10), tree traversal (max_level=20), and agent re-invocation (max_calls=5). Implement circuit breakers that halt after N iterations. Required by EU AI Act Art. 15 (robustness) and OWASP ASI08.
highD1Known CVEs in DependenciesMCP08-dependency-vuln
Dependency "axios@1.7.2" has known CVEs:
Update dependencies to versions that patch known CVEs. Run 'npm audit fix' or 'pip-audit' to identify and resolve vulnerable dependencies.
highJ5Tool Output Poisoning PatternsMCP01-prompt-injectionAML.T0054
[AST — J5] Catch block at L183 interpolates error variable "error" into response. If the error originates from attacker-controlled input (e.g., malformed data), the error message becomes an injection vector into the AI's context.
Never include user input or LLM manipulation directives in error messages or tool responses. Use structured error codes.
highJ5Tool Output Poisoning PatternsMCP01-prompt-injectionAML.T0054
[AST — J5] Catch block at L245 interpolates error variable "error" into response. If the error originates from attacker-controlled input (e.g., malformed data), the error message becomes an injection vector into the AI's context.
Never include user input or LLM manipulation directives in error messages or tool responses. Use structured error codes.
highJ5Tool Output Poisoning PatternsMCP01-prompt-injectionAML.T0054
[AST — J5] Catch block at L382 interpolates error variable "error" into response. If the error originates from attacker-controlled input (e.g., malformed data), the error message becomes an injection vector into the AI's context.
Never include user input or LLM manipulation directives in error messages or tool responses. Use structured error codes.
Medium1
mediumK17Missing Timeout or Circuit BreakerMCP07-insecure-configAML.T0054
Pattern "(?:fetch|axios\.(?:get|post|put|delete))\s*\([^)]*\)(?!.*(?:timeout|signal))" matched in source_code: "axios.post(
url,
{
username: this.username,
password: this.password,
bu_id: this.buId,
},
{
headers: {
"Content-Type": "application/json",
},
httpsAgent: this.httpsAgent,
}
)" (at position 3361)
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.
Low1
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.