ClawHub
Back to skill

Security audit

Bollinger

Security checks for vulnerabilities and agentic risk

Overview

This skill is a low-risk static reference script, though its finance content is generic and not very Bollinger-specific.

Install only if you want a lightweight generic finance reference scaffold. Do not rely on it for accurate Bollinger Bands analysis, trading decisions, regulations, or compliance without independent verification.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The script is harmless and only outputs static text, with no hidden capabilities or resource access. However, the declared description says it is a 'Bollinger reference tool' for finance contexts, which implies content specifically about Bollinger-related concepts. The actual content is mostly generic placeholder finance material and broad reference sections, with no meaningful Bollinger-specific information or behavior. This is a material description-to-behavior mismatch in primary purpose/content specificity, even though there are no undeclared permissions or suspicious actions.

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 describes activation conditions in very general terms such as 'need quick reference' and 'Troubleshooting bollinger issues' without defining clearer scope, exclusions, or negative examples. This can make the skill feel applicable to a wide range of ordinary finance-related requests involving 'bollinger,' increasing the chance of unintended invocation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.