ClawHub

Elixir Dev

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only Elixir/Phoenix helper with normal development examples, though users should review destructive database and deletion examples before applying them.

Safe to install as a development reference. Before running commands or applying generated code, confirm the current project, MIX_ENV, DATABASE_URL, and database target, especially for ecto.drop, ecto.reset, rollbacks, release migrations, formatting, dependency updates, and deletion handlers.

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 (2)

Vague Triggers

Medium
Confidence
87% confidence
Finding
The manifest description is extremely broad ('use for any Elixir or Phoenix development task'), which can cause the skill to be invoked in situations beyond its narrowly intended scope. Over-broad routing increases the chance the agent applies this skill to sensitive coding, deployment, or database tasks without sufficient guardrails, expanding the attack surface and enabling risky actions in inappropriate contexts.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The LiveView example wires a 'delete' event directly to a destructive backend call without showing any confirmation, authorization check, or warning guidance. In an agent skill, examples act as templates; this can normalize unsafe deletion flows and lead downstream users or generated code to omit critical safeguards, resulting in accidental or unauthorized data loss.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal