ClawHub
Back to skill

Security audit

reducto

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Reducto document-processing integration, but users should be aware that documents and extracted data are sent to Reducto and may persist there.

Install only if you are comfortable sending selected documents and extraction instructions to Reducto through Maton. Confirm every upload, edit, hosted function, trigger, or destination before it runs, and avoid the raw MATON_API_KEY path unless the CLI is unavailable.

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 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill documentation gives conflicting statements about the connection authentication model: earlier sections describe OAuth-based login and OAuth2 connections, while the Notes section states Reducto uses API_KEY authentication. In a security-sensitive integration, that inconsistency can cause an operator or downstream agent to choose the wrong credential handling path, potentially exposing long-lived API keys where OAuth tokens and connection-scoped flows were expected, or weakening review/approval assumptions around connection creation and storage.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.