ClawHub
Back to skill

Security audit

Trend Radar

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed weekly trend-report generator with low-impact persistence, though users should be aware it can write reports and events if run or scheduled.

Install only if you want an agent to generate recurring trend reports. Review the output paths and enable any cron schedule intentionally, especially in workspaces where generated files or events may trigger downstream automation.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (3)

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill advertises automatic output to `memory/research/trend-YYYY-WXX.md` and event publication, but does not clearly warn users at invocation time that it will write files and emit events. This can lead to silent persistence of generated content and metadata, which is risky in environments where writes, audit trails, or downstream automations have operational or privacy consequences.

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
- Categories: AI, SaaS, Korean startups, OpenClaw ecosystem
- Weekly change detection + importance score (1-10)
- Result: `memory/research/trend-YYYY-WXX.md`
- Cron integration: Auto-execute every Monday 09:00

## Usage
Confidence
88% confidence
Finding
The cron-based 'Auto-execute every Monday 09:00' enables autonomous operation without an explicit per-run user decision. In context, this is moderately dangerous because each run can perform external searches, generate content, write files, and publish events; if misconfigured or triggered inappropriately, the skill can create unreviewed outputs on a recurring basis.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger phrases are very broad and map to common natural-language requests like 'trends' or 'market trends', which can cause the skill to activate unexpectedly during ordinary conversation. In this skill, unintended activation is more concerning because activation may lead to web searches and downstream file/report generation, increasing the chance of unrequested actions and data writes.

Static analysis

No suspicious patterns detected.