ClawHub
Back to skill

Security audit

Group Activation

Security checks for vulnerabilities and agentic risk

Overview

This skill temporarily lets an owner-invited agent participate in a specific group chat and then close that access again.

Install only if you want the agent to temporarily participate in group chats without requiring every message to mention it. Confirm your OpenClaw owner and group policies are correctly configured, and prefer short durations so the scheduled close action has limited impact if it fails.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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)

Context Leakage

High
Category
Data Exfiltration
Confidence
75% confidence
Finding

Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.

Content

Scanner excerpt · SKILL.md (reported line 16)May include surrounding context.

md
## Procedure

**Step 1 — Capture context**

From the inbound message metadata: platform (e.g. `whatsapp`, `signal`), group ID (the `chat_id` / `from` field), and duration (parse from the owner's message — default 30 minutes if unspecified).

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill explicitly instructs the agent to modify a live, hot-reloaded configuration file to disable requireMention for a group and to schedule an automatic reversion later. That is a real system-state change affecting access control, yet the procedure provides no explicit confirmation, audit, or warning about the security implications of opening the group gate; if parsing, authorization, or scheduling fails, the agent may remain active in the group longer than intended.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.