ClawHub
Back to skill

Security audit

Crypto Snapshot Pro

Security checks for vulnerabilities and agentic risk

Overview

This skill is a clearly disclosed paid crypto-signal service, with financial-risk and third-party-service caveats but no hidden persistence, credential access, or destructive behavior.

Install only if you are comfortable using a third-party paid crypto-signal endpoint. Do not treat its LONG/SHORT/HOLD outputs as financial advice, and verify any trade independently before risking funds.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill facilitates financial decision-making by producing LONG/SHORT/HOLD recommendations with entry, target, and stop levels, but the skill description does not prominently warn users about the risks of relying on such outputs. A brief disclaimer in an example response is insufficient because users may act on the signals as authoritative advice, increasing the risk of financial harm and user deception.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The invocation rule is broad enough that the skill could trigger on generic requests for crypto information without clearly limiting when network calls and paid signal generation should occur. In a financial context, overly permissive triggering increases the chance of unsolicited trading guidance, accidental purchases, or use in situations where the user did not explicitly consent to receiving actionable signals.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
82% confidence
Finding

The skill sends user-supplied asset symbols to an external third-party endpoint, which is a real data transmission outside the local agent boundary. Although the transmitted field is low sensitivity in this example, the call still creates privacy, integrity, and supply-chain risk because responses from the remote service may be misleading, manipulated, unavailable, or monetized through the payment flow.

Content

Scanner excerpt · SKILL.md (reported line 35)May include surrounding context.

When the user asks for a crypto signal, ask for the symbol (BTC, ETH, SOL, etc.) and call the endpoint:

bash
curl -X POST https://crypto-snapshot-pro.onrender.com/ \
  -H "Content-Type: application/json" \
  -d '{"symbol": "SYMBOL"}'

Static analysis

No suspicious patterns detected.