ClawHub
Back to skill

Security audit

Paperzilla Monitor

Security checks for vulnerabilities and agentic risk

Overview

This skill provides disclosed Paperzilla research-brief workflows with narrow, purpose-aligned use of the Paperzilla CLI, Telegram delivery, and minimal per-project deduplication history.

Before installing, confirm you are comfortable with the skill using your authenticated Paperzilla CLI, sending scheduled briefs through the configured chat surface when the profile requires it, and keeping a small per-project history of paper IDs to avoid repeat recommendations.

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)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill explicitly requires a persistent per-project record of previously proposed paper IDs, which creates a durable activity log tied to a project and potentially a user's research interests or workflow. Because the skill provides no retention limits, notice, consent, access controls, or storage location guidance, it risks unnecessary collection and long-term exposure of user/project activity metadata.

Static analysis

No suspicious patterns detected.