ClawHub
Back to skill

Security audit

marine-watch-planner

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple schedule-planning prompt for marine watch routines and does not show hidden data sharing, privileged actions, or persistence.

Before installing, note that the skill may be incomplete because it refers to local reference files and a starter-plan script that are not included. From a security perspective, the inspected artifact is low risk: it is a Markdown-only planner and should only need the scheduling details you choose to provide.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Context Leakage

High
Category
Data Exfiltration
Confidence
75% confidence
Finding

Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.

Content

Scanner excerpt · SKILL.md (reported line 12)May include surrounding context.

md
Build a practical 24h onboard routine that protects sleep, keeps safety anchors, and fits real constraints (role duties, sea state, and limited internet).

## Workflow
1. Capture context inputs.
2. Select watch/sleep model.
3. Generate 24h timeline.
4. Add safety anchors and handovers.

Context Leakage

High
Category
Data Exfiltration
Confidence
75% confidence
Finding

Code or instructions that leak agent conversation context to external services, potentially exposing sensitive user interactions.

Content

Scanner excerpt · SKILL.md (reported line 19)May include surrounding context.

md
Build a practical 24h onboard routine that protects sleep, keeps safety anchors, and fits real constraints (role duties, sea state, and limited internet).

## Workflow
1. Capture context inputs.
2. Select watch/sleep model.
3. Generate 24h timeline.
4. Add safety anchors and handovers.

Static analysis

No suspicious patterns detected.