ClawHub

Jarvis Incident Timeline Writer 01

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only planning skill with a real scope/quality mismatch, but no evidence of unsafe access, persistence, exfiltration, or hidden execution.

Safe to install as a low-risk advisory playbook. Treat it as a generic planning/checklist helper rather than a rigorous incident-forensics timeline tool, and avoid pasting unsanitized secrets, credentials, or sensitive personal data from logs.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Description-Behavior Mismatch

Medium
Confidence
92% confidence
Finding
The skill metadata and name claim it creates incident timelines from logs and notes, but the body defines a generic development planning workflow. This mismatch can cause the agent to invoke the skill in inappropriate contexts, producing unreliable or unsafe outputs during incident handling where precision, chronology, and evidence handling are important.

Vague Triggers

Medium
Confidence
87% confidence
Finding
The description is broad enough to match many ordinary development requests, which increases the chance of over-triggering the skill outside its claimed incident-timeline domain. Overbroad activation can route sensitive or specialized tasks through an unsuitable workflow, leading to poor recommendations and reduced operator trust.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The skill purpose statement says 'Deliver a concrete, reusable workflow for development tasks,' which conflicts with the incident-timeline name and metadata. In security-sensitive workflows, this ambiguity is dangerous because it obscures what the skill is actually for and may cause incorrect activation during incident response or development work.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal