ClawHub
Back to skill

Security audit

documentation-and-adrs

Security checks across malware telemetry and agentic risk

Overview

This skill is a documentation and architecture-decision guide that may write project documentation, with no evidence of hidden execution, credential access, or data exfiltration.

Install this if you want an agent to help write ADRs, README updates, changelogs, API docs, and rationale-focused comments. Review any generated documentation and any proposed git commit, especially because the skill may activate on broad documentation requests.

SkillSpector

By NVIDIA
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
94% confidence
Finding
The trigger list includes very broad terms such as "README" and "documentation," which can cause this skill to activate for many unrelated requests. Over-broad activation increases the chance the agent applies the skill in the wrong context, leading to prompt-scope hijacking, degraded task routing, or unintended instruction influence over normal documentation tasks.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.