ClawHub
Back to skill

Security audit

Implementation Self Review

Security checks for vulnerabilities and agentic risk

Overview

This skill is a bounded implementation self-review checklist with no hidden execution, credential handling, persistence, or network behavior.

Install this if you want Codex to run a structured implementation-quality self-review before delivery. Be aware it can suggest or make scoped code and documentation fixes when you are already in an implementation task, so review resulting edits as you normally would.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The markdown instructs reviewers to check for stale wording using fixed Chinese and English phrase sets. This can bias the skill toward specific languages/locales even when the project uses different languages, and the file does not present this as an opt-in or clearly justified locale constraint.

Content

No source excerpt is available for this finding.