ClawHub
Back to skill

Security audit

Personal Notes

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward personal notes skill that stores and searches notes in a local notes file, with some privacy and activation-scope caveats.

Install this only if you want an agent to keep a persistent local journal in knowledge/personal/notes.md. Be careful with highly sensitive entries, and review or delete that file when you no longer want the information retained.

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
95% confidence
Finding

The skill description includes broad trigger terms such as note, journal, diary, thought, reflection, log, and record, which can cause the skill to activate in conversations where the user did not intend to use persistent note-taking. In this skill's context, unintended invocation is more dangerous because activation can lead to reading from or writing to a personal notes file containing sensitive data.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The natural-language instructions and labels are presented in Russian, which can impose a specific language/locale on users without explicit opt-in. There is no indication that the skill is region-specific or that users may choose another language.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The instructions tell the agent to append user content to knowledge/personal/notes.md, but they do not require informing the user that their input will be stored persistently. In a journaling skill, this is especially risky because users may share highly sensitive personal information without realizing it will be retained and later resurfaced.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.