Jarvis Codebase Mapper 01

Security checks across malware telemetry and agentic risk

Overview

This is a small instruction-only planning skill for codebase mapping and development workflow organization, with no evidence of hidden access, persistence, credential use, or unsafe automation.

This skill is reasonable to install for planning and codebase-orientation work. Review any commands or checklists it suggests before running them, especially in production repositories, because the skill can generate practical command sequences even though it does not execute them itself.

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
91% confidence
Finding
The description is broad enough to activate on many generic development requests, not just codebase mapping. Overly broad activation increases the chance the skill is invoked outside its intended scope, which can bypass more appropriate specialized workflows and lead to irrelevant or lower-quality guidance being applied in sensitive engineering contexts.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The example prompts are generic planning requests that do not anchor usage to codebase mapping. This broadens trigger conditions and can cause the skill to be selected for everyday planning tasks, creating scope confusion and reducing assurance that users receive domain-appropriate instructions.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal