ClawHub
Back to skill

Security audit

Project Methodology

Security checks across malware telemetry and agentic risk

Overview

This is a project-workflow methodology skill that mainly reads and updates project documentation, with some broad discovery and trigger wording users should keep scoped.

Safe to install from an agentic-security perspective. Invoke it explicitly for warmup, planning, recap, or wrapup; keep searches scoped to the current workspace when possible; review any proposed doc writes; and do not approve production, database, API, or local credential-file access unless it is clearly needed in the current task.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (2)

Context-Inappropriate Capability

Low
Confidence
88% confidence
Finding
The quick-reference commands instruct broad home-directory project discovery using `find ~` and `search_files(path="~", ...)`, which can cause unnecessary enumeration of unrelated projects and files outside the current workspace. In an agent setting, this expands data exposure and may surface sensitive filenames or repositories unrelated to the user’s immediate task.

Vague Triggers

Medium
Confidence
91% confidence
Finding
Several triggers are broad regex-like phrases such as `what.*open`, `plan.*feature`, `we.*done`, and `init.*project`, which are likely to match ordinary conversation and activate the skill unintentionally. In an agent environment, accidental invocation can lead to unnecessary file reads, git inspection, or workflow steering the user did not request.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.