ClawHub
Back to skill

Security audit

Subskill Generation Rule

Security checks for vulnerabilities and agentic risk

Overview

This skill only provides file-organization guidance for generated subskill work and does not add executable code, network behavior, credentials, or persistence.

Install this if you want Codex to keep generated subskill scripts and result artifacts in predictable folders. Review the convention if your project uses a different layout, but there is no evidence of hidden execution, data access, or credential handling.

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)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 13)May include surrounding context.

md
4. Add `SKILL.md` inside the feature folder when behavior/usage needs instructions.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The 'When to Use' section lists general situations like 'Creating new subskills' and 'Organizing existing features' without defining specific invocation phrases, boundaries, or negative examples. In a markdown skill description, this can make activation conditions ambiguous and increase the chance of unintended invocation in ordinary development contexts.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.