ClawHub
Back to skill

Security audit

Project Bootstrap

Security checks across malware telemetry and agentic risk

Overview

This instruction-only project scaffolding skill is benign, with a packaging issue that should be fixed so it activates only on explicit project-bootstrap requests.

Install only if you want a local project-bootstrap helper. Use it in a version-controlled or disposable target directory first, review generated files before committing, and prefer a fixed release with explicit trigger phrases instead of the current placeholder trigger metadata.

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
92% confidence
Finding
The trigger field is populated with a non-specific placeholder-like value (`System.Object[]`) instead of concrete activation phrases or constrained conditions. Ambiguous trigger configuration can cause the skill to activate unexpectedly, increasing the chance of unintended execution or invocation in contexts the author did not intend.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.