Back to skill

Security audit

Three Line Dragon Stock

Security checks for vulnerabilities and agentic risk

Overview

This is a plain stock-screening strategy skill with financial-risk concerns but no hidden code, persistence, credential access, or automatic trading behavior.

Review this as an educational stock-selection strategy, not as personalized investment advice. It may cause an agent to answer with actionable trading criteria when stock-screening terms are used, so users should apply their own risk controls and avoid relying on it for real trades without independent financial advice.

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
  • 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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger phrases are broad enough to match ordinary requests for market commentary or stock analysis, causing the skill to activate outside a narrowly intended scope. In context, this increases the chance that users receive prescriptive trading guidance when they did not explicitly ask for a specialized stock-picking strategy, which raises compliance and safety risk.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill gives concrete buy signals, entry criteria, execution language, position sizing, and stop-loss rules without a clear disclaimer that the content is general educational information rather than personalized investment advice. In this context, the skill is expressly designed to drive trading decisions, so users may treat the outputs as actionable recommendations despite lacking suitability checks, risk disclosure, or jurisdiction-specific compliance safeguards.

Content

No source excerpt is available for this finding.