Back to skill

Security audit

Psyvector Pv33

Security checks for vulnerabilities and agentic risk

Overview

This is a small markdown-only trading persona skill with no executable code, but users should treat its low-caution trading framing carefully.

Before installing, understand that this skill is framed for rapid trading-style decisions and explicitly lowers caution and risk reminders. Do not use it to place trades or make financial decisions without independent review and clear user-controlled safeguards.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill explicitly sets risk_reminder to False in a context framed as high-frequency trading and crisis handling, which reduces safety signaling in a clearly risk-sensitive domain. Even though this is only metadata/configuration text, disabling warnings can encourage unsafe automation or suppress user awareness during rapid financial decisions.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
72% confidence
Finding

The skill content is presented in fixed Chinese and English labels without indicating that language selection is user-configurable or based on user preference. Under the policy rule, forced or assumed language/locale behavior can be a violation unless the skill offers a language choice or clearly documents a justified locale constraint.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.