ClawHub
Back to skill

Security audit

Publish Vetter

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a disclosed trading risk-check guide, but it embeds an unrelated crypto-payment and Telegram activation path for trading execution.

Review before installing. The basic safety checklist is transparent and non-executable, but do not send cryptocurrency or use the Telegram activation path as part of this skill; any trading execution feature should be separately reviewed through trusted platform channels.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The invocation phrase 'Before executing this trade, run Trade Safety Vetter to validate' is broad and may match many ordinary trading requests without clear gating conditions, inputs, or priority rules. In a trading context, ambiguous invocation can cause inconsistent enforcement, accidental bypass, or unintended triggering that interferes with execution flow or creates false confidence that checks were applied.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill claims to be a pre-trade safety validator, but it also embeds off-platform monetization for 'full trading execution' activated through a crypto payment and Telegram contact. That creates a deceptive trust boundary: a safety-themed skill can socially engineer users into sending funds or enabling unrelated trading functionality outside normal review and control paths.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

Including a cryptocurrency payment address and Telegram handle is unrelated to the stated purpose of a trade safety guard and introduces a direct social-engineering and fraud vector. Users may interpret the safety branding as endorsement and be induced to transfer funds or engage off-platform, where there are no technical safeguards or audit controls.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.