ClawHub
Back to skill

Security audit

Group Logger

Security checks for vulnerabilities and agentic risk

Overview

This skill is meant to log and summarize LINE group work messages, but it stores raw group-chat history silently and broadly enough that users should review privacy controls before installing.

Install only if the LINE groups are informed that keyword-matching messages will be logged, the CSV and backup files are protected, retention/deletion rules are defined, and summaries are restricted to authorized users and the appropriate group or customer scope.

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 (3)

Missing User Warnings

High
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill is explicitly designed to silently log matching group messages, including sender, group_id, message content, job IDs, and customer names, into a persistent CSV without any notice, consent, retention limits, or access controls. In a group-chat context this creates a real privacy and compliance risk because participants may have no awareness that operational and potentially personal data is being captured and stored for later use.

Content

No source excerpt is available for this finding.

Ssd 3

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill combines persistent collection of group conversations with later retrieval and summarization by customer or job reference, which materially increases the chance of disclosing sensitive operational details to unintended recipients. Because it stores raw messages plus identifiers and supports cross-message aggregation, a mention-triggered summary can expose historical data far beyond what the requester should see, especially in multi-group or shared environments.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The file states that summaries are generated as Thai-language reports, with no indication that users can choose another language or opt in to this locale constraint. This is a natural-language policy issue because it imposes a specific language by default rather than offering user choice.

Content

No source excerpt is available for this finding.