ClawHub
Back to skill

Security audit

业务运营问答助手

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local FAQ knowledge-base helper with disclosed file storage and no evidence of hidden network, credential, or system-level behavior.

Before installing, confirm you are comfortable with FAQ data being stored locally in ~/.faq-bot unless FAQ_BOT_DIR is set, and only import markdown files whose contents are appropriate to reuse in automated answers.

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
  • Rogue AgentSelf-Modification, Session Persistence
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

Session Persistence

Medium
Category
Rogue Agent
Content
## Usage

```bash
# Create knowledge base
python scripts/faqbot.py init

# Import from markdown
Confidence
60% confidence
Finding
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Lp3

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding
The skill advertises and instructs use of local code and file operations, but it does not declare any explicit tool scope such as allowed-tools or permissions. That creates an authorization ambiguity where an agent or orchestrator may grant broader-than-intended access to environment variables and filesystem read/write during FAQ import/export operations.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The activation text is broad enough to trigger on generic requests like 'answer common questions' or 'build a knowledge base,' which could cause the wrong skill to activate in unrelated contexts. In an agent system, over-broad routing can expose file operations and automated answering behavior when the user did not clearly intend to invoke this skill.

Static analysis

No suspicious patterns detected.