ClawHub
Back to skill

Security audit

Shrink JSON in Prompts (TOON Encoder/Decoder)

Security checks for vulnerabilities and agentic risk

Overview

This skill appears to be a straightforward local JSON compressor and decoder with no hidden network, persistence, credential, or destructive behavior.

This skill is reasonable to install for local JSON compression and round-trip conversion. Treat the TOON output as containing the same information as the original JSON, so do not provide secrets or private data unless you intend that content to be processed and possibly pasted into prompts or tool payloads.

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
  • 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
Findings (1)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding

The skill invokes a bundled Python script and explicitly reads input from files or stdin (for example, < input.json), but the manifest declares no permissions or allowed-tools scope. That mismatch weakens least-privilege controls because an agent may use file-reading capability without an explicit declaration, making review and runtime enforcement harder.

Content

No source excerpt is available for this finding.