ClawHub
Back to skill

Security audit

Security Review

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only security review checklist that tells an agent what vulnerabilities to look for, not a skill that accesses credentials or changes the system.

Install only if you want Codex to apply a security-review checklist to code changes. The skill may lead the agent to inspect files you ask it to review, including code that contains secrets, so use normal care when sharing repositories, but the artifact itself does not add hidden execution or persistence.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Credential Access

High
Category
Privilege Escalation
Confidence
60% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 40)May include surrounding context.

md
- API keys, tokens, passwords in code or configs
- Sensitive data in logs
- PII without encryption
- .env files or secrets committed to git

### Configuration
- Debug mode enabled in production

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
75% confidence
Finding

Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.

Content

Scanner excerpt · SKILL.md (reported line 43)May include surrounding context.

md
- .env files or secrets committed to git

### Configuration
- Debug mode enabled in production
- CORS set to wildcard (*)
- Missing security headers
- Default credentials unchanged

Static analysis

No suspicious patterns detected.