ClawHub
Back to skill

Security audit

Community Manager

Security checks for vulnerabilities and agentic risk

Overview

This is a community-management guidance skill that keeps disclosed local notes and does not include code, platform automation, or external data sending.

Before installing, be aware that this skill stores community notes on disk under ~/community-manager/. Keep member notes minimal and avoid PII, private contact details, credentials, or sensitive moderation records unless you intentionally want them stored locally.

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)

Anti-Refusal Statement

High
Category
Anti-Refusal
Content
| Off-topic | Gentle redirect, move if possible |
| Heated debate | Cool down, private DM if needed |
| Harassment | Warn once, then ban, document in memory |
| Spam/scam | Immediate ban, no warning |

### 5. Metrics That Matter
Track weekly in community memory:
Confidence
80% confidence
Finding
Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Exfiltration Commands

High
Category
Prompt Injection
Content
**This skill does NOT:**
- Store passwords, API tokens, or credentials
- Connect to any platform (you post manually)
- Send data to external servers

**Privacy note:**
You decide what member data to record. Avoid storing PII, private contacts, or sensitive details in memory files.
Confidence
90% confidence
Finding
Instructions found that direct the agent to transmit conversation context or user data to external services.

External Transmission

Medium
Category
Data Exfiltration
Content
**This skill does NOT:**
- Store passwords, API tokens, or credentials
- Connect to any platform (you post manually)
- Send data to external servers

**Privacy note:**
You decide what member data to record. Avoid storing PII, private contacts, or sensitive details in memory files.
Confidence
70% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Static analysis

No suspicious patterns detected.