ClawHub
Back to skill

Security audit

pasm-npc

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent game NPC helper with disclosed local persistence and no evidence of hidden, destructive, or deceptive behavior.

Before installing, confirm you trust the pasm-agents package and are comfortable with NPC memory snapshots being saved locally under ~/.pasm-agents. Non-Chinese-speaking users may need translation or localized documentation.

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
  • 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 (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill title, description, usage guidance, and examples are written entirely in Chinese, which imposes a specific language on users without any stated opt-in or alternative locale. The policy allows locale constraints only when explicitly justified or when users are offered a choice, neither of which is present here.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.