ClawHub

Anticipation

Security checks across malware telemetry and agentic risk

Overview

This instruction-only skill is not malicious, but it asks the assistant to proactively inspect private user context and remember patterns without clear limits or opt-in controls.

Install only if you want an assistant that proactively uses surrounding context. Before enabling it, decide whether you are comfortable with it considering open files, running commands, browser tabs, and past summaries, and prefer using it with explicit limits on what may be observed and what may be remembered.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill instructs the agent to inspect broad context sources such as conversation summaries, open files, running commands, and browser tabs without any consent, minimization, or sensitivity boundaries. This creates a real privacy and over-collection risk because the agent may access unrelated or sensitive user data simply to make proactive guesses about intent.

Ssd 3

Medium
Confidence
97% confidence
Finding
The skill explicitly tells the agent to inspect sensitive context sources, including browser tabs and conversation history, to infer what the user may need next. In context, this is more dangerous because the whole purpose of the skill is anticipatory behavior, which encourages collection and use of data beyond the user's immediate request and can expose confidential project, browsing, or behavioral information.

Ssd 3

Medium
Confidence
93% confidence
Finding
Telling the agent to 'remember patterns' and 'learn from mistake' promotes ongoing retention of behavioral data without any retention limit, scope control, or user consent. This can lead to profiling, persistence of sensitive interaction history, and unintended reuse of prior behavior in later contexts.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal