ClawHub
Back to skill

Security audit

TokenSniff

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only crypto token analysis skill that is risky because it discusses speculative trading, but its behavior is disclosed, purpose-aligned, and does not install code, persist, or take account actions.

Install only if you want speculative crypto token research. Treat its BUY/WATCH/AVOID labels and entry suggestions as high-risk analysis, verify all live data independently, and avoid sharing private wallet credentials or using it as financial advice.

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)

Vague Triggers

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger criteria are extremely broad and include ambiguous catch-all phrases such as "similar crypto discovery/analysis tasks" and "always trigger," which can cause the skill to activate for loosely related queries. In a high-risk financial context, unintended invocation can steer users into speculative token analysis, expand unnecessary data access, and crowd out safer or more appropriate handling paths.

Content

No source excerpt is available for this finding.

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
90% confidence
Finding

The directive "Always respond with this structured report" is an anti-refusal pattern because it pressures the agent to comply with the format regardless of safety constraints, uncertainty, or missing data. In this context, it can encourage authoritative financial analysis outputs even when the request is unsafe, unsupported, or should be declined or heavily qualified.

Content

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

Output Format

Always respond with this structured report:

text
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
85% confidence
Finding

The skill instructs use of external sources for web lookups and wallet/address analysis, but the description does not clearly warn that external services may be queried or that blockchain addresses and wallet behavior will be analyzed. This weakens transparency and informed consent, especially in a financial surveillance-style workflow involving third-party sites.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.