ClawHub

IGA Pages

Security checks across malware telemetry and agentic risk

Overview

This IGA Pages deployment skill is mostly coherent, but it needs review because it can steer broad API requests into deployment workflows and tells headless users to pass cloud access keys directly on the command line.

Install only if you intentionally deploy to IGA Pages. Confirm the target project and platform before using it, prefer browser login where possible, avoid pasting long-lived access keys into chat or shell commands, use least-privilege credentials, and treat preview URLs containing tokens as private access links.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The phrase set for API development, such as 'write an API,' 'create an endpoint,' and 'build a backend service,' is highly ambiguous and can capture a large class of general software-engineering requests unrelated to this platform. Because this skill includes deployment and authentication guidance, accidental invocation can steer users into platform-specific setup, credential handling, and deployment flows that exceed the user's original intent.

Vague Triggers

High
Confidence
95% confidence
Finding
The phrase set for API development, such as 'write an API,' 'create an endpoint,' and 'build a backend service,' is highly ambiguous and can capture a large class of general software-engineering requests unrelated to this platform. Because this skill includes deployment and authentication guidance, accidental invocation can steer users into platform-specific setup, credential handling, and deployment flows that exceed the user's original intent.

Ssd 3

Medium
Confidence
97% confidence
Finding
The skill explicitly instructs use of access keys and secret keys on the command line in headless environments, creating a direct path for secrets to be exposed in chat transcripts, shell history, process listings, logs, or agent tool records. In the context of a deployment skill, this is especially dangerous because users may follow the instruction verbatim and disclose long-lived cloud credentials to the agent or execution environment.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal