ClawHub
Back to skill

Security audit

Skill Seo

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only skill for improving ClawHub skill descriptions, with no hidden code or privileged behavior found.

Install only if you want help optimizing ClawHub skill metadata. Review any generated description before publishing, and avoid adding generic trigger phrases unless they are clearly tied to the actual skill capability.

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
90% confidence
Finding

The manifest description packs many broad conversational phrases like 'get more downloads', 'skill marketing', and 'why no one finds my skill' without strong scoping constraints. Because the description is the indexed field used for discovery, overly broad language can make the skill match a wider range of requests than intended, leading to accidental invocation and possible displacement of more appropriate skills.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

This guidance explicitly encourages adding broad trigger phrases such as 'how do I...', 'is there a skill that...', and 'I want to...', which are highly generic and likely to overlap with ordinary user requests unrelated to this skill. In an auto-discovery or semantic matching system, that can cause the skill to be selected outside its intended scope, creating prompt-scope overreach and increasing the chance of unintended activation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.