TODO Tracker (Safe)

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward local TODO tracker that edits a disclosed TODO file and shows no evidence of network access, credential use, or hidden behavior.

Install only if you are comfortable with a persistent local TODO file and occasional automatic summaries of its contents. Avoid putting secrets in TODO entries, and do not set TODO_FILE to an important unrelated document because the script can rewrite the configured file.

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: 93% confidence
Finding: The skill declares broad natural-language trigger phrases and explicitly says it should auto-display a summary during heartbeat, which can cause unintended activation outside clear user consent. In an agent setting, overly permissive triggers increase the chance of the skill running in the wrong context, exposing task contents or modifying TODO state when the user did not intend to invoke this skill.

VirusTotal

60/60 vendors flagged this skill as clean.

View on VirusTotal