ClawHub
Back to skill

Security audit

SCI/SSCI Polishing

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent academic translation and polishing assistant with a bounded preservation-audit helper and no evidence of hidden, persistent, or exfiltrating behavior.

Before installing, expect this skill to produce polished academic English and to prioritize preservation of claims, numbers, citations, and limitations. If you need bilingual output or a non-English final response, state that explicitly when invoking it.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The declared purpose describes a language-generation/editing skill for academic translation and polishing. The supplied code does not translate, rewrite, or improve prose. Instead, it analyzes two text versions and checks whether numeric expressions, citations, and protected terms are preserved exactly. This is a materially different primary purpose: quality-control validation of revisions, not academic translation or SCI/SSCI-oriented polishing. No special permissions are used, but the behavior is clearly mismatched with the description.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The output instruction says to "Return the polished English first," which enforces English as the response language. Because the policy scope includes language/locale violations across all file types, this is a concern when the skill does not explicitly offer the user a language choice or document a justified locale restriction.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The instruction says, "For Chinese input, output English only by default," which imposes a language choice based on input language rather than explicit user preference. This is a natural-language policy concern because it forces a specific locale/language behavior without offering the user an opt-in or alternative.

Content

No source excerpt is available for this finding.