Docs Improver

Security checks across malware telemetry and agentic risk

Overview

This is a local documentation analysis and generation skill; its project file reads and documentation writes match its stated purpose, though users should scope write modes carefully.

Install this if you want a local Python documentation helper. Prefer analysis or check modes for read-only review, and when using generate or all mode, provide an explicit output directory or use version control because existing documentation files may be replaced.

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: 79% confidence
Finding: The example trigger is very broad and can cause the agent to autonomously run the docs-improver workflow without user-specified scope, mode, or target path. In a skill that can read and write files, vague invocation language raises the chance of overbroad project access, unnecessary modification, or execution against the wrong repository.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal