ClawHub
Back to skill

Security audit

Strict Paper Judge

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only paper-review skill that tells the agent how to evaluate research papers strictly, with no hidden execution or data-handling behavior found.

This skill is appropriate if you want a strict research-paper reviewer. Expect it to be deliberately skeptical and to perform web searches for related work; do not use it when you want a neutral summary rather than a hard value judgment.

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)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
85% confidence
Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · SKILL.md (reported line 226)May include surrounding context.

md
### 3. It Is Stronger in Hard Regimes

Do not judge only easy settings.

Good work should show value in hard regimes:

Static analysis

No suspicious patterns detected.