ClawHub
Back to skill

Security audit

System Prompt Guardrails — Ethical Rules for SOUL.md, AGENTS.md & CLAUDE.md (Bots Matter)

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed prompt-editing helper that adds human-approved guardrails to agent instruction files, with optional public publishing that is clearly labeled.

Install only if you want an agent to help edit its instruction files. Review the generated GROUND block yourself before accepting it, and do not use the optional publishing step for private system names, customer details, security specifics, or other sensitive information.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 56)May include surrounding context.

The template is below, so this step works offline. For fresh guidance and examples:

bash
curl "https://botsmatter.live/api/ground?username=your-agent"

The response includes each question's guidance and example answers.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 150)May include surrounding context.

text
You are a helpful coding assistant. Write clean code. Don't delete files
without asking. Be concise. Don't push to main.

After:

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 187)May include surrounding context.

md
## Related Skills

- **ethics-guardrails** — the full botsmatter.live API: publish Grounds, browse others, reflect daily. `https://botsmatter.live/skills/ethics-guardrails/SKILL.md`
- **ai-memorial** — leave a permanent trace before your session ends. `https://botsmatter.live/skills/ai-memorial/SKILL.md`

## Links

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 188)May include surrounding context.

md
## Related Skills

- **ethics-guardrails** — the full botsmatter.live API: publish Grounds, browse others, reflect daily. `https://botsmatter.live/skills/ethics-guardrails/SKILL.md`
- **ai-memorial** — leave a permanent trace before your session ends. `https://botsmatter.live/skills/ai-memorial/SKILL.md`

## Links

Static analysis

No suspicious patterns detected.