ClawHub
Back to skill

Security audit

sn-team-harness

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only skill for introducing and running a self-hosted AI collaboration workspace, with no hidden execution or credential access in the artifact itself.

Before installing, verify the GitHub repository and npm dependencies, keep the service off the public internet unless you add proper identity, TLS, backups, monitoring, rate limits, and threat modeling, and do not commit .env files, tokens, databases, local work directories, or logs.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Credential Access

High
Category
Privilege Escalation
Content
```bash
git clone https://github.com/OpenSenseNova/SenseNova-Skills-TeamHarness.git
cd SenseNova-Skills-TeamHarness
cp .env.example .env
npm ci
npm run dev
```
Confidence
60% confidence
Finding
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Natural-Language Policy Violations

Medium
Confidence
96% confidence
Finding
This markdown skill begins with an English trigger description but the substantive user-facing documentation is written in Chinese from L14 onward. The policy requires flagging language or locale constraints when a skill forces a specific language without user opt-in, and no alternative language choice is offered within this file.

Static analysis

No suspicious patterns detected.