ClawHub
Back to skill

Security audit

Jarvis Incident Timeline Writer 01

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only planning skill with no code execution or persistence, but its instructions are broader than its incident-timeline name suggests.

Installers should understand this skill is more of a general planning checklist than a dedicated incident timeline writer. It is reasonable to use, but the publisher should narrow the description and examples if they want predictable activation only for incident chronology work.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

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 (3)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The skill metadata describes a broad, reusable workflow for general development tasks rather than a narrowly scoped incident timeline function. Overly broad activation language can cause the agent to invoke this skill for unrelated requests, expanding its authority and making its instructions influential outside the intended security-analysis context.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The body of the skill is a generic execution playbook that can apply to many development or operational tasks, with no clear boundaries limiting use to timeline writing. This increases the chance of prompt-surface overreach, where the skill becomes a catch-all procedural template and may override or steer unrelated workflows in ways the user did not intend.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The example prompts use very broad trigger phrases like turning notes into a production-ready plan and running a risk-first action sequence, which are not specific to incident timeline generation. Because examples often influence retrieval or activation, these prompts make accidental invocation more likely for ordinary work-planning requests, broadening the skill's operational reach.

Static analysis

No suspicious patterns detected.