ClawHub
Back to skill

Security audit

Auto Responder

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed auto-reply skill for configured group topics, with some privacy and control settings users should review before enabling.

Before installing, confirm the exact topics, keywords, response templates, mention requirement, and rate limits for each agent. Treat this as a live posting automation: enable it only where automatic replies are acceptable, and periodically clear or inspect the local cache if message-derived metadata retention is a concern.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill documentation and example responses are written to operate in Spanish, and the configured response templates are fixed Spanish outputs such as 'Estoy aquí para apoyar' and '¿Puedo asistir en algo?'. There is no indication that users can opt into another language or that the locale restriction is required for a region-specific purpose, which fits the language/locale policy violation category.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill documents that it records sent-response state in a local cache file but does not clearly warn users that message-derived data may be persistently stored. In a message-monitoring skill that reacts to inbound content across topics, undocumented local retention can expose sensitive conversational metadata or content fragments to other local users, backups, or later forensic access.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.