ClawHub
Back to skill

Security audit

Crypto Prices

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrow live price lookup helper, with some privacy and reliability caveats around broad activation and an external local Python module.

Install this only if you are comfortable with price lookup requests being sent to external market data providers and with the agent running an existing local ~/clawd/crypto_prices.py module that was not part of this reviewed skill package.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The activation guidance is broad enough to trigger on common conversational mentions of prices, which can cause the skill to run in more situations than the user likely intended. Because the skill performs network-backed lookups, over-triggering can leak user query context to external providers, create unnecessary external dependencies, and increase the chance of rate-limit or privacy issues.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The description presents the module as a local source of truth without clearly warning that it contacts Yahoo Finance, CoinGecko, and DexScreener. This can mislead operators into believing the action is purely local, reducing informed consent around network access and data-sharing with third-party services.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.