ClawHub
Back to skill

Security audit

Release Note Drafter

Security checks for vulnerabilities and agentic risk

Overview

This is a simple release-note drafting skill with no commands, credentials, persistence, or hidden data access.

Install this if you want help drafting release notes from change lists. Review inputs before use if your commits or issues contain private information, because the skill is intended to process whatever change text you provide.

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
Confidence
90% confidence
Finding
The skill description uses broad activation language ('should be used when turning raw commits, merged pull requests, issue lists, or plain change notes into concise user-facing release notes') without clear boundaries or stricter invocation criteria. In an agent marketplace or automatic skill-routing context, this can cause the skill to trigger on overly broad inputs, increasing the chance of inappropriate activation, accidental processing of sensitive development artifacts, or interference with more specialized skills.

Static analysis

No suspicious patterns detected.