Algernon Sprint

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed study-sprint workflow that reads and updates a local OpenAlgernon flashcard database, with no evidence of hidden or unrelated behavior.

Install this only if you want the agent to access the specified local OpenAlgernon study database, shuffle cards across all materials, update review scheduling, and log sprint results. Confirm the database path and sqlite3 dependency first.

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 (1)

Vague Triggers

Medium

Confidence: 88% confidence
Finding: The trigger phrases are broad enough to activate on common study-related requests, which can cause the skill to run when the user did not explicitly intend to start a timed sprint. In an agentic system, unintended activation can disrupt user workflows, cause surprising behavior, and lead to inappropriate access to local study data or state-changing review actions.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal