ClawHub
Back to skill

Security audit

backtest-expert

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only finance backtesting skill with disclosed Finskills API use and no local code, persistence, or hidden behavior.

Install only if you are comfortable using Finskills for market data. Avoid entering confidential strategy details or proprietary symbol baskets unless you are comfortable with the provider seeing the API queries and have reviewed its privacy and retention practices.

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
93% confidence
Finding

The README encourages users to submit strategy hypotheses, symbols, and benchmark requests while describing external API-backed data retrieval, but it does not clearly disclose that user-provided trading ideas and identifiers may be transmitted to third-party services. In a finance-oriented skill, strategy concepts can be commercially sensitive, so missing disclosure can lead to unintended sharing of proprietary or confidential investment research.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger phrase "Build a walk-forward test for my golden cross strategy" is relatively generic and could overlap with ordinary discussion about trading ideas rather than a clearly bounded invocation phrase. The README provides example triggers but does not define activation boundaries, exclusions, or negative examples to clarify when the skill should or should not activate.

Content

No source excerpt is available for this finding.