ClawHub
Back to skill

Security audit

Psyvector Pv17

Security checks for vulnerabilities and agentic risk

Overview

This skill is very vague but contains only a short markdown description and no code, install scripts, persistence, credential handling, or data access instructions.

Before installing, treat this as a lightly specified persona/protection skill rather than a concrete security tool. The main limitation is unclear scope: it does not explain exactly when it should activate or what actions it should take.

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 (2)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The manifest description is only "System protection," which is a very broad capability statement and does not define concrete trigger phrases, scope boundaries, or exclusion conditions. In a markdown/manifest context, this ambiguity can cause the skill to match many ordinary safety or system-related requests unintentionally.

Natural-Language Policy Violations

Low
Confidence
75% confidence
Finding
The document presents the skill identity and description in fixed Chinese and English sections, but does not state that the user can choose a preferred language or locale. This may conflict with language/locale policy expectations if the skill defaults to a specific language presentation without explicit opt-in.

Static analysis

No suspicious patterns detected.