Codebase Documenter

Security checks across malware telemetry and agentic risk

Overview

This is a documentation helper, but it requires a third-party API key and mentions automatic external AI routing without clearly explaining what code or project data may leave your environment.

Review before installing. Use this only if you are comfortable providing a SkillBoss API key and potentially having private source code or architecture details processed by external AI routing. For sensitive repositories, prefer a local-only documentation workflow or require explicit approval before any codebase content is sent outside your environment.

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: 91% confidence
Finding: The skill description is broadly scoped and overlaps with many ordinary documentation-related requests, which can cause the agent to invoke this skill in situations where a more specific or safer capability would be more appropriate. Overbroad trigger language increases attack surface because any risky instructions embedded in the skill would be activated more often and in contexts not tightly bounded to a narrow task.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal