ClawHub
Back to skill

Security audit

Tech Trend Radar

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed trend-reporting workflow that researches public technology signals and writes structured reports, with no evidence of hidden or unsafe behavior.

Before installing, understand that this skill may run fresh web research and create saved report/event files when invoked. Enable scheduled runs or downstream event-bus automation only if you want recurring trend reports.

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 (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The example trigger phrases are very broad, natural requests such as weekly reports, model rankings, and SaaS/AI changes, which can match ordinary user prompts and cause the skill to auto-activate outside narrowly intended contexts. Because this skill drives web research and report generation, unintended activation can alter agent behavior, consume resources, and inject a fixed reporting workflow when the user did not explicitly request this specific skill.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill description is broad enough to match many common requests about technology, markets, products, and regulation, which increases the chance the agent invokes this skill in situations where a narrower or safer skill would be more appropriate. Over-broad activation can cause unintended data collection, excessive external research, or workflow/file side effects such as writing reports and publishing events when the user only asked a general question.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The trigger examples use ordinary phrasing like 'What changed in SaaS and AI this week?' and 'Write this week's AI trend report,' which are likely to overlap with everyday analytical prompts. This makes accidental invocation more likely, and because the skill includes side-effecting behaviors like saving reports to memory and emitting event files, misuse can alter state or trigger downstream automations unexpectedly.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
71% confidence
Finding

The natural-language examples present only English trigger phrases even though the surrounding documentation is Chinese, which can indicate an implicit language preference rather than offering the user a choice. The file does not state that users may interact in their preferred language or that output language is configurable.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.