ClawHub
Back to skill

Security audit

date-count

Security checks for vulnerabilities and agentic risk

Overview

This is a simple countdown skill that stores dates in a local JSON file, with no executable code, network behavior, or hidden privileged actions found.

Install only if you are comfortable keeping countdown names and dates in a local JSON file. Avoid storing sensitive personal dates there, and back up the file before bulk edits because deleting entries or reusing a name can change or overwrite saved countdowns.

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
Category
Not specified by scanner
Confidence
92% confidence
Finding

The single-item query examples are phrased as ordinary natural language requests such as asking how long until a birthday, which can easily overlap with routine conversation and cause unintended invocation. In an agent environment, overly broad triggers increase the chance the skill activates on unrelated user messages and exposes or manipulates countdown data without the user explicitly intending to use this skill.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The listing triggers like viewing all countdowns or all anniversaries are broad and weakly scoped, so common phrasing could accidentally trigger bulk disclosure of all stored entries. Because this action returns the full set of stored reminders, accidental invocation has greater privacy impact than a single-item query.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The markdown instructs users to directly edit a persistent JSON file and notes that duplicate names overwrite existing dates, but it does not clearly warn that manual modification or deletion affects stored user data. Since the skill behavior includes persistent file changes, a user-facing warning about data loss or overwrites is warranted.

Content

No source excerpt is available for this finding.