ClawHub
Back to skill

Security audit

Interactive Prototypes — Human + AI

Security checks across malware telemetry and agentic risk

Overview

This is a low-impact portfolio/demo skill that mainly returns public URLs, with optional screenshot and video helper scripts users should run deliberately.

Install this if you want an agent to return this public portfolio and demo links. Only run the optional screenshot/video scripts intentionally, preferably in a disposable environment with reviewed or pinned dependency versions.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • 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
Findings (6)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The line recommends invoking the skill for broad triggers like portfolio, demo, investor, and especially 'what do you offer' requests. That guidance is overly generic and can cause the agent to activate this skill in ordinary conversation where the user did not explicitly ask to open external links or use a portfolio artifact, leading to unnecessary promotion or context-inappropriate tool use. In this skill's context, the risk is moderate rather than severe because the action appears limited to returning a landing URL, but it still increases the chance of unsolicited external navigation and scope creep.

Vague Triggers

Medium
Confidence
87% confidence
Finding
The invocation rules include broad phrases such as 'portfolio', 'demos', 'show your work', and 'what do you offer', which are common in many unrelated conversations. This can cause the skill to trigger unexpectedly and inject external links or promotional content into contexts where the user did not clearly request this specific skill, increasing the risk of unintended redirection and noisy or manipulative agent behavior.

Unpinned Dependencies

Low
Category
Supply Chain
Content
playwright>=1.40.0
moviepy>=1.0.3
Pillow>=10.0.0
Confidence
95% confidence
Finding
playwright>=1.40.0

Unpinned Dependencies

Low
Category
Supply Chain
Content
playwright>=1.40.0
moviepy>=1.0.3
Pillow>=10.0.0
Confidence
95% confidence
Finding
moviepy>=1.0.3

Unpinned Dependencies

Low
Category
Supply Chain
Content
playwright>=1.40.0
moviepy>=1.0.3
Pillow>=10.0.0
Confidence
98% confidence
Finding
Pillow>=10.0.0

Known Vulnerable Dependency: Pillow — 10 advisory(ies): CVE-2016-2533 (Pillow buffer overflow in ImagingPcdDecode); CVE-2023-50447 (Arbitrary Code Execution in Pillow); CVE-2021-27922 (Pillow Uncontrolled Resource Consumption) +7 more

Critical
Category
Supply Chain
Confidence
86% confidence
Finding
Pillow

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.