ClawHub
Back to skill

Security audit

Freqtrade Strategy Dev

Security checks for vulnerabilities and agentic risk

Overview

This skill is a plain Markdown guide for Freqtrade strategy development, with a routing-scope concern but no hidden execution, persistence, or credential behavior.

Install this only if you specifically want help with Freqtrade cryptocurrency strategy development. Treat the trading examples as educational starting points, backtest and dry-run before any live use, and consider narrowing the generic trigger phrases to avoid accidental activation for unrelated strategy questions.

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
  • 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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger phrases are broader than the skill’s narrow domain and could cause the agent to invoke this trading-strategy skill for generic requests about 'improve strategy' or 'why is my strategy losing'. That creates misrouting risk: unrelated prompts may be handled by a skill that gives cryptocurrency trading guidance, increasing the chance of unsafe, irrelevant, or financially consequential output.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.