ClawHub
Back to skill

Security audit

SlipBot

Security checks across malware telemetry and agentic risk

Overview

SlipBot is a local note-management skill that writes and updates notes in a slipbox folder, with some accidental-capture risk from its shorthand prefixes.

Install this only if you want prefixed messages to be saved into a local slipbox and used to update note metadata and the graph index. Run it from the directory where you want the slipbox created, avoid starting sensitive or unrelated messages with the capture prefixes, and consider reviewing or backing up the slipbox before relying on automatic graph cleanup.

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)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill directs the agent to create and modify files in the user's working directory and slipbox without any explicit user-facing confirmation or warning that filesystem state will be changed. In an agent setting, silent writes can cause unintended persistence, overwrite note metadata, or alter adjacent project files if the computed working directory is broader than expected.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
This maintenance flow authorizes deletion-style changes to the graph index and clearing entries from missing.md based on inferred file absence, again without explicit user warning or approval. If the graph or missing list is incorrect, corrupted, or manipulated, the skill could silently remove valid index data and destroy auditability of what was marked missing.

Vague Triggers

Low
Confidence
82% confidence
Finding
The activation rule applies whenever user content starts with a defined prefix, which is broad enough to trigger on ordinary chat text, bullets, quotations, or journal-like messages not intended for persistence. In this skill, overbroad invocation increases risk because activation leads directly to file creation, linking, and graph updates.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.