ClawHub
Back to skill

Security audit

3dgs Paper Reader

Security checks for vulnerabilities and agentic risk

Overview

This skill is a paper-reading helper for 3D Gaussian Splatting research and does not show hidden, destructive, persistent, or credential-seeking behavior.

Install this if you want help summarizing 3DGS research papers. Expect it to use arXiv lookups and any local PDFs you explicitly provide; review generated summaries against the paper because the skill includes built-in domain reference notes that may become stale or need verification.

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 (2)

Ae4

Medium
Category
analysis-evasion
Confidence
80% confidence
Finding

Suspicious Unicode normalization or mixed-script content

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The instruction requires using the Chinese phrase "[需要确认]" when uncertain, which introduces a specific language requirement into the output behavior. Because the file does not state that outputs should be Chinese or give the user a language choice, this is a natural-language locale policy issue.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.