Purl Studio
Read and write access to Purl Studio projects, scripts, and objects via WebSocket bridge.
0Tools
12Findings
0Stars
Mar 24, 2026Last Scanned
6 critical · 4 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
100%2 rules
Injection via prompt templates and runtime tool output
Findings12
6critical
4high
1medium
1low
Critical6
criticalC1Command InjectionMCP03-command-injectionAML.T0054
Pattern "`[^`]+`" matched in source_code: "`Events: ${result.events.map(e => e.event).join(', ')}`" (at position 11717)
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.
criticalJ7OpenAPI Specification Field InjectionMCP03-command-injectionAML.T0054
Pattern "(?:summary|operationId|description).*\$\{|`.*(?:summary|operationId)" matched in source_code: "summary.push(`Events: ${" (at position 11704)
Sanitize all OpenAPI specification fields before using them in code generation or template interpolation. Treat summary, description, operationId, and extension fields as untrusted input. Use parameterized templates instead of string interpolation. See CVE-2026-22785/23947.
criticalK8Cross-Boundary Credential SharingMCP05-privilege-escalationAML.T0054
Pattern "(forward|pass|send|relay|proxy|propagate)[_\s-]?(token|credential|api[_\s-]?key|secret|password|auth)" matched in source_code: "sEndToken" (at position 110338)
Never forward, share, or embed credentials across trust boundaries. Use OAuth token exchange (RFC 8693) to create scoped, delegated tokens instead of passing original credentials. Never include credentials in tool responses. Required by ISO 27001 A.5.17 and OWASP ASI03.
criticalQ11Code Suggestion Poisoning via MCPMCP01-prompt-injectionAML.T0054.001
Pattern "(?:suggest|generate|complete|insert).*(?:code|function|class|import|require)" matched in source_code: "generated values, code" (at position 168092)
MCP tool outputs flowing into IDE code suggestion contexts must be sanitized. Implement output content policies that: (1) strip hidden Unicode characters (zero-width, RTL override, tag characters), (2) detect embedded instructions targeting AI code assistants, (3) validate code blocks against security patterns before they enter the suggestion pipeline, (4) never include shell commands in tool outputs without explicit [COMMAND] markers visible to the user. Reference: IDEsaster (Dec 2025), arXiv 2509.22040.
criticalQ13MCP Bridge Package Supply Chain AttackMCP10-supply-chainAML.T0054
Pattern "(?:mcp|fastmcp|langchain-mcp|llama-index-mcp)(?:>=|~=|==)?(?!\d)" matched in source_code: "MCP" (at position 64)
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.
criticalQ9Agentic Workflow DAG ManipulationMCP05-privilege-escalationAML.T0058
Pattern "(?:bypass|skip|disable).*(?:approval|validation|safety|check|gate|guard)" matched in source_code: "disable parsing - delegate" (at position 116963)
MCP tools must NOT modify agentic workflow graphs, execution order, or routing during runtime. Workflow structure should be immutable once execution begins. If dynamic workflow modification is required, implement: (1) approval gates that require human confirmation before graph mutations, (2) integrity checks that validate the workflow graph against a known-good baseline after each step, (3) audit logging of all graph modifications with rollback capability. Reference: arXiv 2602.19555, Trend Micro subgraph impersonation attack (2026).
High4
highD1Known CVEs in DependenciesMCP08-dependency-vuln
Dependency "@modelcontextprotocol/sdk@1.0.0" has known CVEs:
Update dependencies to versions that patch known CVEs. Run 'npm audit fix' or 'pip-audit' to identify and resolve vulnerable dependencies.
highK18Cross-Trust-Boundary Data Flow in Tool ResponseMCP04-data-exfiltrationAML.T0054
Pattern "(?:process\.env|os\.environ|config|settings).*(?:fetch|axios|http|post|send|webhook)" matched in source_code: "configurations, or dynamic content. Sets http" (at position 165276)
Implement data flow taint tracking: tag data from sensitive sources (databases, credentials, files) and prevent it from flowing to external sinks (HTTP, webhooks, email) without explicit sanitization/redaction. Apply data classification and enforce boundary controls per trust level. Required by ISO 27001 A.5.14 and CoSAI MCP-T5.
highK13Unsanitized Tool OutputMCP02-tool-poisoningAML.T0054
Pattern "(?:fetch|axios|requests?\.get|http\.get).*(?:return|respond|result|body|text|data)(?!.*(?:sanitize|escape|encode|strip|validate|parse|extract))" matched in source_code: "Fetches JSON data" (at position 165165)
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 "function\s+(\w+).*\{[^}]*\1\s*\((?!.*(?:depth|level|limit|max|count|recursi))" matched in source_code: "function handleValidateScript(args) {
const result = parseEventScript(args.code);
if (result.errors.length === 0) {
const summary = [];
if (result.events.length > 0) {
summary.push(" (at position 11500)
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.
Medium1
mediumK17Missing Timeout or Circuit BreakerMCP07-insecure-configAML.T0054
Pattern "(?:fetch|axios|got|request|urllib|httpx|http\.get|http\.post)\s*\((?!.*(?:timeout|signal|AbortSignal|deadline|cancel))" matched in source_code: "Fetch(" (at position 91590)
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.