ClawHub
Back to skill

Security audit

Ai Prompt Arsenal

Security checks for vulnerabilities and agentic risk

Overview

This prompt-only skill is mostly transparent, but it includes broad activation wording and a deployable crypto trading bot prompt without adequate safety boundaries.

Review this skill carefully before installing if you use agents for finance, crypto, or code generation. It does not contain executable malware or persistence, but it can steer an agent toward generating deployable crypto trading automation without enough warnings or guardrails. Treat generated trading code as unsafe for live use unless independently reviewed, sandbox-tested, and configured with secure secret handling.

A.I.G

Vulnerability Patterns
  • 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
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill description is extremely broad, covering content creation, NFT art, music, crypto research, business automation, and code generation without clear activation boundaries. In an agent environment, this increases the chance the skill is invoked for generic user requests and can override or interfere with more appropriate, narrower skills, which may lead to unsafe prompt generation in sensitive domains like code or crypto.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill includes a prompt specifically to generate a full Python crypto trading bot with exchange integration, risk parameters, and webhook notifications, which materially expands the skill from harmless prompt templating into facilitating executable financial automation. In the context of a prompt library, this can enable users to produce unsafe or insufficiently reviewed trading code that may place real trades, mishandle credentials, or cause financial loss without any embedded safeguards or review requirements.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The prompt asks for production-style trading-bot code and even states 'No trading advice — purely technical implementation,' which removes one disclaimer while still enabling high-risk automation. The absence of user-facing warnings about live-market, exchange API, credential, and system risks makes the skill more dangerous because it normalizes direct generation of deployable financial code without cautionary context.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.