Security audit

A Stock N Pattern

Security checks for vulnerabilities and agentic risk

Overview

This paid stock-signal skill is presented as real-time market screening, but the included API returns hard-coded stock recommendations with a fresh timestamp and lacks the documented payment enforcement.

Review carefully before installing or paying. Treat the returned stocks, targets, stop losses, and volume data as unverified static examples unless the publisher supplies auditable live-data provenance, source timestamps, and real x402 payment enforcement.

A.I.G

Vulnerability Patterns

Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally

Findings (2)

other

Error

Location: api.py:10
Finding: Static stock recommendations are presented as current market signals
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Warning

Location: api.py:37
Finding: Payment verification is absent and the API binds to all network interfaces
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Tp4

High

Category: MCP Tool Poisoning
Confidence: 96% confidence
Finding: The skill metadata and prose claim real-time N-pattern stock screening and backend-processed market intelligence, but the artifact shown contains only declarative configuration and marketing claims, with no verifiable analysis logic. This creates a trust and payment-integrity risk: users or agents may pay for a financial signal service based on unverifiable behavior, misleading provenance, and unclear data handling, which is especially sensitive because it influences trading decisions and triggers on-chain payment.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The module docstring and returned API content are entirely Chinese-language and A-share specific, with no indication that users can select another language or locale. This creates a natural-language locale policy issue because the skill appears to enforce a specific language/market context without explicit opt-in or justification in the file.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 83% confidence
Finding: The description is written only in Chinese ("A股N字型态信号 API - x402付费版本"), which may impose a language expectation without any opt-in or explanation that the skill is intended only for a Chinese-speaking or China-market context. The policy allows locale constraints when they are explicitly justified, but this manifest does not state that limitation.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.