ClawHub
Back to skill

Security audit

Risk Guardian

Security checks for vulnerabilities and agentic risk

Overview

This appears to be a legitimate Paradex risk-analysis skill, but it can read sensitive account and vault data and its trigger wording is broader than clearly necessary.

Install only if you are comfortable with the skill reading Paradex account, vault, position, balance, market, funding, and orderbook data to produce risk reports. Use it for explicit Paradex risk questions, and verify critical liquidation or margin numbers in the Paradex UI before acting.

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill’s activation text includes broad conversational triggers like “am I safe,” “should I be worried,” and “check my risk,” which can match ordinary user phrasing beyond clear Paradex-specific intent. This can cause accidental invocation in unrelated contexts, pulling sensitive account or vault data unnecessarily and increasing the chance of privacy-impacting or confusing tool use.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.