ClawHub

Algernon Review

Security checks across malware telemetry and agentic risk

Overview

This skill is a local flashcard review assistant that predictably updates a study database and review log as part of its stated purpose.

Install only if you are comfortable with the skill modifying your local OpenAlgernon study database and appending local session logs. Review generated correction or promotion cards, and periodically delete or back up the ~/.openalgernon data if your study topics are sensitive.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
96% confidence
Finding
The trigger phrases are broad enough to match ordinary user conversation such as asking to review cards, which can cause the skill to activate unexpectedly. Because this skill performs database reads/writes and session logging, accidental invocation can lead to unintended local state changes rather than being a harmless routing issue.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill is designed to insert correction cards, update review metadata, promote cards, and append to conversation logs without an explicit upfront warning or consent boundary. If triggered unintentionally or used in an ambiguous context, it can silently modify the user's local database and persistent memory, creating integrity and privacy concerns.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal