ClawHub
Back to skill

Security audit

Report Builder

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent report-building helper with local templates and scripts, though users should be aware that some triggers are broad and one workflow can initiate web research through another skill.

Install only if you want an agent to help create and update executive briefing files. Review requests that match broad briefing/report terms, and confirm before allowing any digital-research workflow to fetch external information for internal or sensitive reports.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Confidence
93% confidence
Finding
The trigger set contains broad everyday phrases like 'executive summary', 'report builder', and similar generic business terms, which can cause the skill to activate on ordinary requests without clear user intent. Unintended invocation matters because this skill can reshape content, create files, and influence downstream tooling, increasing the chance of context hijacking or unwanted file operations.

Missing User Warnings

Low
Confidence
92% confidence
Finding
The workflow describes automatically triggering another skill to perform web_search and web_fetch when a TODO marker appears, but it does not mention user awareness, consent, or any guardrails around external network access. This can cause unexpected outbound requests, pull in untrusted external content, and create privacy/compliance issues if internal project context is sent to external sources.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
91% confidence
Finding
The trigger '简报' is extremely short and generic, making accidental activation likely during normal Chinese-language requests. Even though the skill's function is not inherently high risk, broad unintended routing can still misapply templates, alter outputs, or invoke supporting file operations without explicit consent.

Static analysis

No suspicious patterns detected.