ClawHub
Back to skill

Security audit

RocketChat

Security checks for vulnerabilities and agentic risk

Overview

This Rocket.Chat skill is a transparent REST API command reference, but it can read and change chat workspace data when used with a powerful token.

Install this only for a Rocket.Chat workspace you intend the agent to manage. Prefer a limited-scope token when possible, and review before running commands that delete messages, archive channels, create users, post messages, or invoke webhooks.

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 (3)

External Transmission

Medium
Category
Data Exfiltration
Content
- RC_TOKEN
        - RC_USER_ID
      bins:
        - curl
      anyBins:
        - jq
    primaryEnv: RC_TOKEN
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium
Category
Data Exfiltration
Content
```bash
# List channels
curl -s -H "X-Auth-Token: $RC_TOKEN" -H "X-User-Id: $RC_USER_ID" \
  "$RC_URL/api/v1/channels.list?count=50"

# Channel info
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Missing User Warnings

Medium
Confidence
84% confidence
Finding
This markdown file documents operations such as archiving channels, deleting messages, creating users, and searching/listing message history, but it does not include any cautionary warning about modifying user data or accessing potentially sensitive chat content. For markdown skills, the guidance calls for warnings when behavior could affect user data, privacy, or system integrity.

Static analysis

No suspicious patterns detected.