Superpowers (OpenClaw)

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only skill about an AI coding workflow, with disclosed external install examples but no hidden code, credentials, or data access in the reviewed artifact.

Treat this as a lightweight guide, not a complete bundled implementation. Before running the clone or plugin install examples, verify the upstream Superpowers repository and understand that installing it may add persistent behavior to your local coding tool.

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: 86% confidence
Finding: The trigger phrases are very broad and overlap with ordinary software-development requests such as code review, refactoring, and TDD. In an agent environment, this can cause unintended or excessive activation of the skill, which may override user intent, alter workflow selection, or introduce unexpected prompt context into unrelated tasks.

VirusTotal

59/59 vendors flagged this skill as clean.

View on VirusTotal