ClawHub
Back to skill

Security audit

OnChain Analysis

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed blockchain-analysis prompt with no executable code, persistence, or hidden data access; its main caveat is somewhat broad activation wording.

Use this skill for blockchain transaction and wallet analysis, and verify that invocations include an onchain context and transaction-level evidence. Treat its findings as analytical hypotheses, especially for financial or compliance decisions.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The manifest lists short natural-language triggers such as "analyze wallet," "trace transactions," and "detect anomaly" without explicit scope constraints or exclusion conditions. These phrases are broad enough to overlap with everyday support, finance, security, or data-analysis requests, which could cause unintended invocation of this skill.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The 'When to Use' section uses open-ended phrases like 'seems suspicious or unclear' and 'before a decision' without defining scope, exclusions, or concrete trigger phrases. Because this is a markdown file, ambiguous activation guidance falls under vague triggers and may overlap with many general analysis requests.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.