Back to skill

Security audit

crypto-drt-scalping

Security checks for vulnerabilities and agentic risk

Overview

This is a local Markdown trading-strategy reference with documentation inconsistencies but no executable payload, credential use, persistence, or hidden high-impact behavior.

Install only if you want a static crypto-trading reference. Treat the backtest and win-rate claims cautiously, verify any referenced scripts or data separately before relying on them, and do not connect this guidance to real trading accounts without independent review.

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
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 (3)

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest description at L003 claims the skill covers 12 crypto pairs, but the body documentation elsewhere states '18 pairs total' and lists additional instruments such as ATOM, LTC, DOT, and OP. This is an active contradiction within the skill's own documentation about what the backtest reference actually includes.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The description and metadata notes include Danish phrases such as '100% lokal backtest-reference — ingen netværkskald, ingen API-nøgle' alongside English content. This imposes a locale/language assumption without explicit user opt-in or a stated region-specific justification.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

L098 says the backtest script is for '7 pairs' while L099 says the database contains '12 pairs', and earlier documentation claims both 12 pairs and 18 pairs total. These conflicting statements create intent/documentation divergence about the real scope of the skill's backtest assets.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.