Ariadne Thread

Security checks across malware telemetry and agentic risk

Overview

This documentation-only skill helps create and maintain AI navigation files, with broad activation wording but no hidden code, credential use, network transfer, or destructive behavior.

Install this if you want an agent to add and maintain AGENTS.md, module INDEX.md files, file intent headers, and related docs. Review generated project guidance before committing it, because those files can steer future agent behavior and should be scoped to the repo and kept free of secrets.

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 (2)

Vague Triggers

Medium

Confidence: 93% confidence
Finding: The trigger text is extremely broad and includes generic phrases like creating or updating AGENTS.md, project navigation, module boundaries, and structuring new projects. This can cause the skill to activate in many ordinary coding situations outside its narrow intended scope, steering the agent into unnecessary behavior and increasing the chance of inappropriate file creation or modification.

Vague Triggers

Medium

Confidence: 88% confidence
Finding: The file defines very broad natural-language triggers such as "documentation sync", "update docs", and especially "iteration end" that can cause the agent to launch a multi-step documentation workflow. Because these phrases can appear in ordinary user conversation or unrelated requests, the skill may execute unintended batch updates, expanding scope and causing unauthorized or surprising modifications.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal