ClawHub
Back to skill

Security audit

Clawsec Feed

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed security-advisory feed installer and checker, with network downloads and local state that fit its stated purpose.

Before installing, review the shell snippets, verify the GitHub release source and signed checksums, and be aware that the skill may read local installed skill names and keep a small local state file for advisory tracking.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Description-Behavior Mismatch

Medium
Confidence
80% confidence
Finding
The metadata claims risk code was removed and emphasizes safety, but the skill still instructs the agent to download artifacts and modify local files. This mismatch can mislead users and reviewers about the true behavior and reduce scrutiny of code that performs installation actions.

Vague Triggers

Medium
Confidence
76% confidence
Finding
Very broad trigger keywords such as 'feed', 'package', 'security', and 'advisory' increase the chance the skill activates in unrelated contexts. Unintended activation is risky here because the skill includes exec-capable installation and network-fetch workflows.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.