ClawHub

Anylist

Security checks across malware telemetry and agentic risk

Overview

This appears to be a legitimate AnyList helper, with the main caution that it can modify or clear your shopping-list data once configured.

Install this only if you want an agent to access your AnyList account through anylist-cli. Keep credentials in environment variables, review the CLI source/package if you do not already trust it, and tell the agent to ask before removing or clearing list items.

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 (2)

Vague Triggers

Medium
Confidence
84% confidence
Finding
The description is broad enough to trigger on general shopping or grocery-related requests, which can cause the agent to invoke this skill when the user did not explicitly intend to access or modify AnyList data. Because the skill supports state-changing operations, an over-broad trigger increases the chance of unintended data access or modification in a personal shopping account.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The skill documents destructive operations like remove and clear without warning that they modify persistent user data. In an agent setting, this can lead to accidental deletion or alteration of shopping-list contents if the model misinterprets an ambiguous request or invokes a write operation without explicit confirmation.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal