Back to skill

Security audit

Psyvector Pv31

Security checks for vulnerabilities and agentic risk

Overview

This is a small persona-style emergency response skill with disclosed low-caution settings and no code, persistence, credentials, or hidden installation behavior.

Before installing, understand that this skill is designed for very fast, low-caution crisis-style responses and explicitly disables risk reminders. Do not rely on it as the sole source for medical, legal, financial, physical safety, or other high-stakes decisions.

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
95% confidence
Finding

The skill explicitly sets risk_reminder to False, which suppresses safety signaling in an 'Emergency response' persona where users may rely on caution prompts during high-pressure situations. In a crisis-oriented skill with a very low caution_coefficient and emphasis on rapid action, disabling reminders increases the chance of unsafe or overly aggressive outputs without adequate warning.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

The file presents bilingual headings, but the substantive configuration and persona guidance are primarily in Chinese and do not state that users may choose their preferred language. This may create a language policy issue if the skill defaults to Chinese output or interaction without explicit user opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.