ClawHub
Back to skill

Security audit

Plagiarism Checker

Security checks for vulnerabilities and agentic risk

Overview

This skill runs a local heuristic originality check on user-provided text or files, with documentation accuracy caveats but no hidden network, persistence, credential, or destructive behavior found.

Before installing, treat the results as rough heuristics rather than authoritative plagiarism or AI-detection evidence. Only provide files you intend the tool to read, and be aware that some documented options and detection methods are inaccurate or not implemented.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding

The skill instructs the agent to process user-supplied text from a file via --file, which implies file-read capability, but it does not declare any permissions or allowed-tools scope. That mismatch weakens least-privilege controls and can let the runtime or orchestrator grant broader file access than users or reviewers expect, increasing the risk of unintended local file exposure if the skill is invoked with attacker-influenced paths.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The example report hard-codes the timestamp using the "CST" locale/timezone format, which implies a specific regional setting. The file does not indicate that users can choose their locale or that this region-specific formatting is required for a justified purpose.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The argument help says the reference file contains 'one URL/per line', implying external sources or URL-based plagiarism checking. In reality, the code simply reads each line from the file and uses those lines directly as comparison strings in the local similarity function, with no URL fetching or web lookup.

Content

No source excerpt is available for this finding.