ClawHub
Back to skill

Security audit

Paper Reproduction by Python

Security checks for vulnerabilities and agentic risk

Overview

This skill is a plain Markdown workflow for reproducing papers in Python, with expected local file reads and project outputs but no hidden execution or persistence.

Install this if you want a structured paper-reproduction workflow that may read local paper sources and create code, logs, results, figures, and both English and Chinese README files in the target project. Review or override the bilingual README requirement if you only want documentation in one language.

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
Confidence
93% confidence
Finding
The skill explicitly requires generating and maintaining a Chinese README alongside the English README, regardless of whether the user requested bilingual output. This can override user preferences, increase unnecessary work, and cause unintended disclosure or policy issues in contexts where language choice matters, though it is not inherently a security-critical issue.

Static analysis

No suspicious patterns detected.