ClawHub
Back to skill

Security audit

Strategy Translator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed trading-strategy translation and research helper with repo-editing capability, but no hidden execution, persistence, credential handling, or exfiltration behavior was found.

Before installing, treat this as a trading strategy migration and research-writing assistant that may edit code and docs. Review generated strategy logic, validation assumptions, and repository changes carefully, especially before relying on outputs for financial decisions or live trading.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill metadata says it is for strategy translation, but the body expands the scope into broader trading research workflows and reproducible deliverable generation. This mismatch can cause an agent to invoke the skill for tasks beyond its declared purpose, increasing the chance of over-broad file modification, unsafe planning, or unauthorized code generation under a narrower trust boundary.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The outputs and workflow instruct the agent to produce end-to-end plans, validation design, repo-ready code, docs, and run commands, which materially exceeds simple cross-framework strategy translation. In an agent setting, this scope expansion can be exploited to justify broad repository edits and research/code-generation actions that users or policy may not expect from a translation skill.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.