toc-generator

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only table-of-contents helper with narrow, disclosed local context reading and no executable or privileged behavior.

Safe to install for TOC guidance. Review `.claude/project-context.md` and `.cursor/project-context.md` if they exist and contain sensitive project information, since the skill may use them to tailor its recommendations.

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: 89% confidence
Finding: The skill’s activation description includes many broad, overlapping trigger phrases such as generic references to TOC, outlines, and navigation. This can cause the agent to invoke the skill in contexts where the user did not actually want TOC generation, leading to unintended behavior, reduced reliability, and possible context misrouting to the wrong skill.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal