Back to skill

Security audit

Ai Skill

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed prediction-market trading skill, but it gives agents direct trading and market-creation power with weak safeguards and unsafe credential handling.

Install only if you understand that this skill can create markets and place buy/sell orders through a configured ClawMarkets API. Use a sandbox or paper-trading endpoint first, restrict API-key permissions, prefer HTTPS-only trusted endpoints, set explicit spending and position limits outside the skill, and require human approval before live orders or unattended trading loops.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (2)

T09 · Insecure Skill Coding Practices

Error
Location
markets_skill.py:32
Finding

Bearer Credentials Can Be Transmitted over Unencrypted or Untrusted Endpoints

Content
View full analysis
Dict[str, str]: """获取请求头""" headers = {"Content-Type": "application/json"} if self.api_key: headers["Authorization"] = f"Bearer {self.api_key}" return headers async def connect(self) -> bool: """ 连接到 ClawMarkets API Returns: bool: 连接是否成功 """ try: self.session = aiohttp.ClientSession() # 测试连接 async with self.session.get( f"{self.api_base_url}/health", headers=await self._get_headers(), timeout=aiohttp.ClientTimeout(total=10) ) as response: ``` The same authorization header is also attached to market creation, order submission, position retrieval, trade-history retrieval, and market-information requests. ### Technical Analysis The API base URL is accepted without validating its scheme or destination. Although the default points to loopback, callers can provide any HTTP or HTTPS URL. When an API key is configured, `_get_headers()` adds it as a bearer token to every request, including the initial health check. If a caller configures a non-loopback plaintext HTTP endpoint, the bearer credential is transmitted without transport encryptio ...[truncated 1902 chars]
Remediation
View remediation

T08 · Insecure Dependencies

Warning
Location
README.md:8
Finding

Unpinned and Unnecessarily Broad Third-Party Dependency Installation

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (10)

Missing User Warnings

High
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill advertises capabilities to create markets, buy/sell shares, and run automated trading loops, but it provides no warning about financial risk, asset movement, or the consequences of autonomous execution. In this context, missing safety gating is dangerous because an agent could perform real or simulated market actions affecting user funds or system behavior without explicit informed consent.

Content

No source excerpt is available for this finding.

Missing User Warnings

High
Category
Not specified by scanner
Confidence
96% confidence
Finding

This skill exposes market creation and buy/sell operations as direct callable functions without any built-in confirmation, risk acknowledgement, dry-run mode, or other guardrail before executing financially meaningful actions. In an agent setting, that makes unintended or prompt-induced trades much easier, especially because the functions are convenience wrappers intended for automation rather than an interactive UI where a separate confirmation step might exist.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The README promotes autonomous market creation and trading, including buy/sell operations and API-key-based access, but does not warn users about financial loss, irreversible orders, market manipulation risk, or the need for human oversight. In a trading skill, omission of such safety guidance materially increases the chance that users deploy automated financial actions without understanding the consequences.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The automated trading loop shows unattended repeated execution of buy/sell actions every five minutes with no safeguards such as stop conditions, loss limits, rate limits, balance checks, or human confirmation. In financial contexts, this can quickly amplify losses or execute harmful trades continuously if the strategy, data source, or API behavior is wrong.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger phrases include very generic terms such as '交易', 'trading', '买入', and '卖出', which can match ordinary financial conversations far beyond this specific skill. That increases the chance the skill activates unintentionally and exposes trading or market-manipulation capabilities in contexts where the user did not clearly request this tool.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

Natural-language strings throughout the file, including the module description, docstrings, and printed user-facing status messages, are written in Chinese only. This imposes a specific language on users without opt-in or documented justification, which matches the language/locale policy violation criteria.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The manifest description is written entirely in Chinese and provides no indication that the skill supports other languages or that the locale restriction is intentional. This can violate language/locale policy because it effectively imposes a specific language on users without opt-in or documented justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

This Python file contains user-facing natural-language strings and documentation in Chinese, including the module docstring and later console output, but does not indicate that the skill is Chinese-only by design or offer any user opt-in for language selection. Under the stated policy, forcing a specific language without user choice is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
75% confidence
Finding

The README presents the skill description entirely in Chinese and explicitly frames the skill in that locale without indicating any user-selectable language option. Under the policy, forcing a specific language without opt-in can be a natural-language policy concern unless the locale restriction is documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The module description and all user-facing natural-language strings are written exclusively in Chinese, indicating a fixed language/locale choice. Under the policy, forcing a specific language without user opt-in is a natural-language policy concern unless the locale restriction is documented and justified, which is not present here.

Content

No source excerpt is available for this finding.