ClawHub
Back to skill

Security audit

Urlencode Tool

Security checks for vulnerabilities and agentic risk

Overview

This is a simple local URL encode/decode helper, but its documentation claims several options the included script does not support.

Install only if you need simple single-string URL encoding or decoding. Do not rely on the documented batch, JSON, charset, query, or path-safe features unless the package is updated to implement them or the documentation is corrected.

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)

Tp4

High
Category
MCP Tool Poisoning
Confidence
92% confidence
Finding

The core purpose matches: the script encodes and decodes URL text, including plus-style handling for form-like space encoding. However, the description overstates capabilities. The code only accepts a single string via command-line flags and does not process files or batches. Its 'component' option allows encoding with safe='' but does not clearly implement general 'partial encoding' as described. There are no undeclared risky behaviors or extra resource accesses, but the declared feature set does not accurately match the implemented functionality.

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.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The manifest claims broader functionality than the code implements, including form-data handling, partial encoding controls, and batch file processing. This script only accepts a single --encode or --decode string plus basic component/plus modes, with no file input/output or batch-processing logic.

Content

No source excerpt is available for this finding.