ClawHub
Back to skill

Security audit

Vane Daily Market Report

Security checks for vulnerabilities and agentic risk

Overview

The skill is a finance-reporting prompt that openly describes portfolio data and publishing, but it does not clearly limit or confirm publishing of sensitive balances and P&L.

Review carefully before installing. Use this only for user-directed report generation, keep publishing draft-only by default, and confirm that balances, P&L, account identifiers, and recommendations are redacted or explicitly approved before sending to Telegram, Substack, email, or other external channels.

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)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill advertises automated publishing and includes portfolio/account balance reporting without warning users about sensitive financial data handling or the risk of publishing private information to external channels. In context, this increases the chance that account balances, position P&L, or trading signals could be disclosed unintentionally through Telegram, Substack, or other connected services.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

This markdown file describes the skill's purpose and capabilities but does not specify how or when it should be invoked, nor does it provide bounded trigger phrases or exclusions. That absence can make activation conditions overly broad or ambiguous in systems that infer invocation from the description.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.