Back to skill

Security audit

blockchain-all-rounder

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only blockchain helper skill with no executable code, credential collection, persistence, or hidden system access, though its trigger terms are broad for financial and security topics.

Before installing, understand that this skill may activate for common crypto terms and can provide financial-adjacent and smart-contract security guidance. Treat its outputs as informational, verify live prices and on-chain facts independently, and never provide private keys, seed phrases, wallet passwords, or signing authority.

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
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 (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

All user-facing natural-language content in the file is Chinese, and the skill does not indicate that users may interact in other languages or opt into this locale. Under the policy, forcing a specific language without user opt-in is a natural-language policy concern unless the locale limitation is explicitly justified.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger list is broad and consists of very common blockchain terms such as BTC, ETH, DeFi, and Web3, which can cause the skill to activate during ordinary discussion rather than only when the user clearly intends to invoke it. In a security-sensitive skill that gives trading, wallet-analysis, and smart-contract guidance, accidental invocation increases the chance of users receiving authoritative-seeming financial or security advice out of context.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger list includes very broad, high-frequency terms such as "BTC", "ETH", "DeFi", "Web3", and generic Chinese phrases like "区块链" and "行情分析", which can cause the skill to activate in many loosely related conversations. This expands the skill’s reach beyond clearly intended contexts, increasing the chance of unintended routing, user confusion, and exposure of users to specialized financial or security guidance when it was not explicitly requested.

Content

No source excerpt is available for this finding.