ClawHub
Back to skill

Security audit

Daily Review Dashboard

Security checks for vulnerabilities and agentic risk

Overview

This skill manages a local daily trading review dashboard and only shows expected local file edits, with no evidence of hidden execution, network access, or credential handling.

Install this only if you want an agent to maintain Steven's local review_egg daily review dashboard and update its related data files. Review the generated changes when adding new daily reviews, because the skill coordinates several persistent files and does not itself require a preview or backup step.

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
93% confidence
Finding
The trigger description goes beyond explicit invocation phrases and includes broad behavioral conditions like submitting review content or discussing trading mistakes and emotions. This increases the chance the skill will activate in situations the user did not clearly intend, which can lead to unintended reads/writes across the review_egg workspace and accidental modification of personal review data.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill instructs the agent to write or update multiple local files, including HTML, JSONL, CSV, and summary trackers, but does not require any user warning, preview, or confirmation before persistent changes. In this context, the skill manages a personal reflection system, so unintended activation or parsing mistakes could silently corrupt records, overwrite data, or introduce inconsistent state across several dependent files.

Natural-Language Policy Violations

Low
Confidence
79% confidence
Finding
Key trigger phrases, labels, and workflow terms are presented in Chinese, and the skill appears to assume Chinese-language interaction. There is no indication that the user can opt into another language or that the Chinese-only constraint is required by a documented regional use case.

Static analysis

No suspicious patterns detected.