ClawHub
Back to skill

Security audit

Vaunt signals

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed paid crypto-trading signal lookup, with no local persistence, hidden execution, or evidence of data theft or destructive behavior.

Install only if you want an agent to call Vaunt's external service for crypto trading signals and you understand that some routes spend USDC via x402 and return financial recommendations, not guaranteed investment advice. Confirm before paid calls and avoid connecting a wallet or signer you do not want used for these requests.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (4)

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · README.md (reported line 2)May include surrounding context.

md
Publishable copy of railway/src/agent/SKILL.md (the served route /agent/SKILL.md is the source of truth).
Sync before publishing: cp railway/src/agent/SKILL.md skills/vaunt-signals/SKILL.md
Publish: npx clawhub@latest login --no-browser   (device flow, approve in the browser once)
         npx clawhub@latest skill publish ./skills/vaunt-signals --slug vaunt-signals --categories trading --topics x402,hyperliquid,trading,signals

Rp1

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The description uses broad, natural-language trigger phrasing such as asking whether something is 'a buy right now,' which could cause an agent platform to invoke the skill in situations the user did not explicitly intend. In this context, unintended invocation is more sensitive because the skill is tied to paid x402 routes and trading advice, so accidental use could trigger unnecessary paid calls or surface financial recommendations unexpectedly.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.