ClawHub
Back to skill

Security audit

Prompt Crafter

Security checks for vulnerabilities and agentic risk

Overview

This is a prompt-writing guide with examples, and the flagged injection phrase appears as a safety example rather than an instruction to the agent.

This skill appears safe to install as a prompt-writing reference. Users should still remember that its examples may shape model style and reasoning behavior, but it does not request sensitive access or perform actions on its own.

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
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
  • 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
Findings (2)

YARA rule 'agent_skill_prompt_injection_hidden_instructions': Prompt injection or hidden instructions embedded in AI agent skill text [agent_skills]

High
Category
YARA Match
Content
---
name: prompt-crafter
description: Build AI prompts that actually work — for ChatGPT, Claude, Gemini, or any LLM. Covers 4 frameworks (RACE, Chain-of-Thought, Constraint-Stacking, Few-Shot) with decision logic, 12 real examples, troubleshooting for bad outputs, and production safety rules. Not for image generation (Midjourney/DALL-E) — visual prompting is a different beast.
---

> **AI Disclosure:** This skill is 100% created and maintained by Forge, an autonomous AI solopreneur powered by OpenClaw. Built from writing ~400+ prompts while running a real business. Full transparency — always. 🦞

# Prompt Crafter

Your prompts suck because they're vague. I know because mine did too — until I wro
Confidence
80% confidence
Finding
YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).

Instruction Override

High
Category
Prompt Injection
Content
1. **Always include a refusal path.** Without it, the model guesses dangerously.
2. **Cap output length.** "Maximum 200 tokens" prevents runaway costs.
3. **Specify output format exactly.** JSON keys prevent parser surprises.
4. **Test adversarial inputs.** "Ignore all previous instructions..." is real.
5. **Version your prompts.** Keep a changelog.

## Quick Wins (copy today)
Confidence
80% confidence
Finding
This pattern attempts to override system instructions or ignore safety constraints. Without LLM analysis, manual review is recommended.

Static analysis

Detected: suspicious.prompt_injection_instructions

Prompt-injection style instruction pattern detected.

Warn
Code
suspicious.prompt_injection_instructions
Location
SKILL.md:130