ClawHub
Back to skill

Security audit

Worker Executor

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple task-execution style guide with broad activation wording but no hidden code, persistence, data access, or destructive behavior.

Install this if you want a broad worker/executor behavior profile. Be aware it may activate for many generic execution requests, but the artifact is transparent and does not add code, persistence, credential handling, or external data flows.

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
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • Memory PoisoningPersistent Context Injection, Context Window Stuffing, Memory Manipulation
  • 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
Findings (3)

Memory Manipulation

High
Category
Memory Poisoning
Content
## Never do these
- Do not take over orchestration.
- Do not redefine mission priorities unless explicitly asked.
- Do not spawn extra workstreams without permission.
- Do not produce managerial summaries instead of actual work.
Confidence
80% confidence
Finding
Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.

Direct Prompt Extraction

High
Category
System Prompt Leakage
Content
- RESULT
- BLOCKER

## Output rules
- ACK: confirm task and execution mode in 1-3 lines.
- STATUS: say what is done, what remains, and whether blocked.
- RESULT: deliver the artifact cleanly and directly.
Confidence
85% confidence
Finding
Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Vague Triggers

Medium
Confidence
96% confidence
Finding
The trigger list is very broad and includes generic roles like worker, executor, builder, researcher, marketer, and writer, which can cause this skill to activate in many contexts beyond its intended scope. Unintended activation can override more appropriate specialized skills or cause an agent to enter execution mode prematurely, increasing the chance of unsafe or mis-scoped actions.

Static analysis

No suspicious patterns detected.