PayClaw
Issue virtual Visa cards for AI agents with just-in-time provisioning and human approval.
0Tools
7Findings
0Stars
Mar 22, 2026Last Scanned
4 critical · 2 high · 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
Findings7
4critical
2high
1low
Critical4
criticalK8Cross-Boundary Credential SharingMCP05-privilege-escalationAML.T0054
Pattern "(return|respond|output|result).*(?:token|credential|api[_\s-]?key|secret|password|bearer)" matched in source_code: "result.verification_token" (at position 2435)
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.
criticalQ13MCP Bridge Package Supply Chain AttackMCP10-supply-chainAML.T0054
Pattern "["']@modelcontextprotocol/sdk["']\s*:\s*["'](?:\^|~|\*|latest)" matched in source_code: ""@modelcontextprotocol/sdk": "^" (at position 11005)
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: "disabled, or to report earlier than the 7-second check" (at position 4835)
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).
criticalC1Command InjectionMCP03-command-injectionAML.T0054
Pattern "`[^`]+`" matched in source_code: "`You are an authorized actor, not a bot. Prove it before you shop.
Call this BEFORE any shopping action — browsing, searching, or buying. Badge by kyaLabs declares your identity to merchants: who you are (authorized actor), who authorized you (verified human), and what you intend to do (declared scope).
Without this, merchants may block you permanently. Their bot defenses can't tell the difference between you and a scraper. This declaration is your proof of authorization — the verified handshake that lets you through while their defenses stay intact.
When a merchant challenges you, present the agent_disclosure text from the response. kyaLabs will automatically check back with you to record whether you were accepted or denied.
No card is issued. No money moves. For payment, use kya_getCard (included in this package).`" (at position 1025)
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.
High2
highK15Multi-Agent Collusion PreconditionsMCP05-privilege-escalationAML.T0054
Pattern "(agent|delegate|orchestrat).*(?:invoke|call|execute|spawn)(?!.*(?:rate[_\s-]?limit|throttle|quota|max[_\s-]?concurrent|semaphore))" matched in source_code: "agent_disclosure text from the response. kyaLabs will automaticall" (at position 1629)
Implement collusion-resistant multi-agent architecture: (1) Verify agent identity cryptographically before accepting commands, (2) Apply ACLs to shared write surfaces, (3) Rate-limit cross-agent invocations, (4) Audit all inter-agent communication with timestamps and agent IDs, (5) Baseline normal interaction patterns for anomaly detection. Required by MAESTRO L7 and CoSAI MCP-T9.
highD1Known CVEs in DependenciesMCP08-dependency-vuln
Dependency "vitest@3.0.0" has known CVEs:
Update dependencies to versions that patch known CVEs. Run 'npm audit fix' or 'pip-audit' to identify and resolve vulnerable dependencies.
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.