ClawHub
Back to skill

Security audit

academic-literature-summary

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Chinese academic-paper summarizer with optional DOCX/PDF output and no hidden execution or persistence.

Install this if you want Chinese structured summaries of academic literature. Before asking for DOCX or PDF output, confirm where the file will be written and avoid overwriting existing work.

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 (4)

Natural-Language Policy Violations

Medium
Confidence
95% confidence
Finding
The instructions explicitly require that the summary body be in Chinese and the manifest description also says the skill outputs a Chinese concise summary. This imposes a language policy on users without stating that they can choose another language or opt in to Chinese output.

Natural-Language Policy Violations

Medium
Confidence
86% confidence
Finding
The document title and throughout the structure contract prescribe a Chinese-language output format and Chinese labeling, but do not indicate that the user may choose another language or that the restriction is region-specific. This can violate language/locale policy when a skill forces a specific language without user opt-in.

Natural-Language Policy Violations

Medium
Confidence
92% confidence
Finding
The style contract specifies Chinese as the primary language by default, which can override or ignore a user's language preference and reduce transparency about output constraints. This is a policy/quality vulnerability rather than a code-execution issue: it can cause the agent to produce inaccessible or non-user-aligned output, especially for users expecting English or another language.

Missing User Warnings

Low
Confidence
82% confidence
Finding
The skill states that it supports outputting summaries as DOCX/PDF documents, which implies creating files that may affect user data or workspace. The markdown description does not include any warning or disclosure about file creation behavior, destination, or possible overwrite implications.

Static analysis

No suspicious patterns detected.