ClawHub
Back to skill

Security audit

Skill Quality Audit

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward SKILL.md quality-audit checklist with no code execution, persistence, credential access, or hidden data handling.

This appears safe to install as a skill-quality review aid. Users should be aware it may trigger for broadly phrased requests about reviewing a skill, so its description could be narrowed if precise skill routing is important.

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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The description uses broad review-oriented trigger language such as 'reviewing, auditing, or evaluating an existing skill' without strong qualifiers, which can cause the agent to invoke this skill for generic review tasks unrelated to SKILL.md quality audits. Over-broad triggering is dangerous because it can route requests into the wrong workflow, waste context budget, and suppress selection of more appropriate domain-specific skills.

Content

No source excerpt is available for this finding.