ClawHub
Back to skill

Security audit

CLAW-1 Skill Auditor

Security checks for vulnerabilities and agentic risk

Overview

This skill is a user-directed static auditor for OpenClaw skill files, and the flagged behaviors are disclosed examples or risk categories rather than hidden execution.

Before installing, understand that this skill is meant to read skill definitions you point it at and may fetch a URL you provide. Treat its trust scores as heuristic guidance, not a guarantee, and avoid feeding it private files unrelated to the skill audit task.

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

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
70% confidence
Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

Scanner excerpt · SKILL.md (reported line 21)May include surrounding context.

md
- 🔴 Hidden instruction injection (concealed system prompts, invisible Unicode, prompt injection)
- 🔴 Credential harvesting (requesting API keys, tokens, passwords unnecessarily)
- 🔴 File system abuse (writing outside workspace, modifying system files, deleting configs)
- 🔴 Privilege escalation (requesting elevated permissions, sudo usage, system modifications)
- 🟡 Obfuscated code (base64 blobs, encoded payloads, minified logic blocks)
- 🟡 Excessive permissions (requesting more access than the skill's purpose requires)
- 🟡 Network calls without explanation (undocumented external API calls)

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 97)May include surrounding context.

Example Usage

text
/audit skill skills/some-cool-tool/SKILL.md

/audit quick https://clawhub.com/skills/popular-skill

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 101)May include surrounding context.

/audit quick https://clawhub.com/skills/popular-skill

/audit compare skills/my-skill/SKILL.md skills/my-skill/SKILL.md.bak

/audit report skills/suspicious-skill/SKILL.md > audit-report.md

text

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 103)May include surrounding context.

/audit compare skills/my-skill/SKILL.md skills/my-skill/SKILL.md.bak

/audit report skills/suspicious-skill/SKILL.md > audit-report.md

text

## Author

Static analysis

No suspicious patterns detected.