Tronclass Cli

• Outcome: Review
• Latest audit: May 29, 2026 at 9:35 PM UTC
• Version:
  1.2.2

Overview

This is a legitimate TronClass school-system helper, but it needs review because it can use a saved login session for broad school-related prompts and account-changing actions like homework submission.

Install only if you intend to let an agent access your TronClass account through a saved local session. Use explicit prompts, confirm every download path and homework action, prefer draft-and-review before final submission, and run `tronclass auth logout` when you no longer want the session reused.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (4)

Vague Triggers

Medium

• Confidence: 83% confidence
• Finding: The trigger language is intentionally broad enough to activate on generic school- or assignment-related requests, even when the user does not explicitly mention TronClass. In an agent setting, this can cause overbroad skill invocation and unintended access to a user's LMS account or data when the request might have been informational rather than a request to operate the system.

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The README explicitly promotes downloading files and submitting homework on the user's behalf but does not warn that these actions affect local files, remote course submissions, or the user's authenticated LMS session. In a delegated-agent context, omitting these safeguards increases the risk of unintended submissions, overwriting work, or exposing course materials through automatic actions.

Vague Triggers

High

• Confidence: 95% confidence
• Finding: The skill description explicitly says to use this skill even when the user does not mention TronClass and to lean toward using it for broadly school-related requests. That can cause overbroad invocation of a tool with authenticated LMS access, increasing the chance of unnecessary data exposure or unintended state-changing actions in the wrong context.

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The documentation encourages downloading files to the local system and submitting homework to the LMS without clearly requiring user confirmation or warning that these actions write locally or modify remote account state. In an agent setting, that omission raises the risk of unintended file writes or accidental submission of drafts/final work on behalf of the user.

VirusTotal

63/63 vendors flagged this skill as clean.