ClawHub
Back to skill

Security audit

Daily Note Helper

Security checks for vulnerabilities and agentic risk

Overview

This skill reorganizes user-provided notes into summaries and tasks, with no code, network access, or persistence; implicit activation is the main thing to be aware of.

Install only if you are comfortable with the agent automatically selecting this skill for rough daily notes. Review sensitive meeting notes or personal reflections before sharing them with any agent, but this package itself does not add code execution, network transfer, or persistence.

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
  • 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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill enables implicit invocation without any trigger constraints or exclusion conditions, which can cause the agent to activate on loosely related user input and process content the user did not explicitly intend to send to this skill. In a note-organizing skill, this creates a real prompt-scope and privacy risk because rough notes, chat fragments, or meeting content may contain sensitive personal or business information that gets automatically routed or transformed without clear user consent.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The file presents user-facing language in both Chinese and English, but does not indicate whether the user can choose a preferred language or locale. This can create an implicit language policy mismatch if the skill assumes one language without explicit user opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.