ClawHub
Back to skill

Security audit

Y2k Aesthetic Generator

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward Y2K image-generation skill that calls a disclosed third-party image API, with some privacy and token-handling cautions but no hidden persistence or destructive behavior.

Install only if you are comfortable sending your prompt, optional reference image UUID, and Neta API token to the Neta/TalesOfAI service. Use non-sensitive prompts and avoid running the documented --token form on shared systems where command history or process listings may expose secrets.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding
The skill declares only `Bash`, but its documented usage invokes a Node script that sends prompts and optional reference identifiers to the external Neta API, indicating network-capable behavior that is not transparently declared. This can mislead users and platforms about the skill's actual data flows, reducing informed consent and weakening permission-based controls.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The invocation guidance is very broad—'use when someone asks to generate or create y2k aesthetic photo generator images'—without boundaries, exclusions, or privacy cautions. Overbroad triggers can cause the skill to be selected in situations where user content, sensitive photos, or identifiers are sent to an external image API without the user clearly intending that handoff.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The description markets the image-generation capability but does not warn users that their prompts and optional reference-image UUIDs are sent to an external API. This omission undermines user awareness and consent, especially when prompts may contain personal data or when reference identifiers link to private assets.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The script requires an API token to be passed via the --token command-line argument and does not warn users that CLI arguments may be exposed through shell history, process listings, logs, or job runners. This can leak credentials to other local users or operational tooling, especially on shared systems or CI environments.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.