ClawHub

Generate ASCII Art

Security checks across malware telemetry and agentic risk

Overview

This is a low-impact ASCII art helper with overly broad trigger examples but no evidence of hidden, destructive, credential-seeking, or persistent behavior.

Install only if you want an ASCII art generation helper. Before relying on it in a busy agent environment, remove or tighten the broad trigger phrases, especially the numeric-only trigger, and make sure the referenced local capability_executor.py is trusted.

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 (3)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The trigger examples include generic terms like "ASCII艺术", "字符画", and especially "文字画", which can plausibly appear in normal conversation outside a tightly scoped skill invocation. This creates unintended activation risk, where the skill may intercept unrelated requests and route them to a tool capability without sufficiently explicit user intent.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The activation text includes vague help-seeking phrasing such as users needing help with a generated skill identifier, which lacks clear behavioral boundaries and can match broad support-style queries. In an agent environment, this increases the chance of accidental or contextually inappropriate invocation, especially because the surrounding file shows auto-merged, noisy trigger content.

Vague Triggers

High
Confidence
97% confidence
Finding
Using a standalone numeric token like "59" as a trigger is highly overbroad and likely to collide with ordinary user input, references, counts, or identifiers. This can cause frequent false activations and misrouting, and because the skill is wired to a capability executor, unintended tool execution becomes more likely than with a purely informational skill.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal