ClawHub
Back to skill

Security audit

PSN Assistant

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward PlayStation helper that uses public websites and a small user-requested deal watchlist, with minor activation and retention caveats.

Install only if you are comfortable with the skill checking public third-party gaming sites and saving watched deal details when you ask for reminders. Be aware that generic words like "trophy" or "new release" may trigger it unexpectedly, and review or delete memory/psn-watchlist.json if you no longer want saved deal reminders.

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
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger list includes broad, commonly used terms such as "trophy," "platinum," and "new release," which can match normal conversation and cause the skill to activate outside a clearly PlayStation-specific context. Unintended activation can lead to unnecessary web scraping, irrelevant responses, and accidental invocation of other behaviors such as persistence features, increasing privacy and safety risk in multi-skill environments.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill instructs saving user watchlist data to persistent storage (memory/psn-watchlist.json) but does not clearly disclose persistence, retention, scope, or obtain explicit consent before writing data. This creates a privacy risk because users may believe they are making a transient request when their preferences and activity history are actually stored for later processing and reminders.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.