ClawHub
Back to skill

Security audit

Human Writing

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation style guide with no code execution, network access, credential handling, persistence, or destructive behavior.

Install this if you want Codex to apply a stricter professional documentation style. Review the style preferences first, because it may make README, technical explanation, and code-comment output more terse and opinionated than your usual voice.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The workflow uses broad trigger phrases such as "write documentation," "create a README," or "explain this technically," which can cause the skill to activate in situations the user did not explicitly intend. This is not directly a security exploit, but it can override user-preferred style, increase unintended prompt routing, and create opportunities for prompt-instruction interference across tasks.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

The description enforces a specific writing standard, including stylistic rules like "no emojis" and a fixed "Professional Human in the Field" mode, without indicating user choice of language or locale. This can be read as forcing a single communication style by default rather than offering opt-in or documenting justified scope.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.