ClawHub
Back to skill

Security audit

Paper Reading Research Framing

Security checks for vulnerabilities and agentic risk

Overview

This is a research-writing workflow skill that reads selected research artifacts and writes framing documents in a local workspace, with no hidden execution or credential behavior found.

Before installing, understand that the skill will guide an agent to inspect selected local research artifacts and create/update Markdown framing files. Point it only at research material you want used for paper positioning, and review its generated claim-safety and citation-support outputs before relying on them.

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

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

Line L008 mixes English with the Chinese phrase "形成论文表达 / 研究定位 / 引用支撑" as part of the usage motivation. This can be read as a language/locale preference in the skill description, but the file does not say that language choice is optional or limited to a justified region-specific context.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.