ClawHub
Back to skill

Security audit

PR Description Generator / PR 描述生成

Security checks across malware telemetry and agentic risk

Overview

This skill is a simple PR-description helper with no executable payload, install actions, persistence, or evidence of hidden data movement.

Before using it on private repositories, review diffs and commit history for secrets, internal URLs, customer data, or personal metadata. The current artifact is minimal and does not show where generated content is processed, so treat repository content as potentially sensitive when asking any agent or external tool to summarize it.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill explicitly says it generates PR descriptions from git diff and commit history, but it provides no warning that those inputs may contain sensitive source code, secrets, internal URLs, or personal metadata. In an agent context, this omission can cause users to submit repository data to downstream tooling or models without realizing the privacy and confidentiality implications.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.