ClawHub
Back to skill

Security audit

adserFB5

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent competitor-ad research playbook with disclosed external lookups and competitor-memory use, but users should be aware it saves research for future comparisons.

Before installing, confirm you are comfortable with the skill using external search and ad-scraping tools and saving competitor names, URLs, ad angles, and notes into memory for future reports. For one-off research, ask the agent not to save findings if your environment supports that control.

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
93% confidence
Finding

The trigger phrases "tìm đối thủ" and especially "xem thị trường" are broad enough to match ordinary business or market-research requests, which can cause this skill to activate unintentionally. In this skill, unintended activation matters because it initiates external searches, ad-library lookups, and persistent competitor-memory writes, potentially causing unnecessary data collection and workflow side effects.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The instructions and example triggers are written to assume Vietnamese usage, and the report template is fully in Vietnamese, but the file does not tell users they may choose another language. This creates a locale-policy concern because the skill appears to impose a specific language by default without explicit opt-in or justification.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly instructs the agent to persist competitor research into memory but does not warn the user that this storage will occur. This creates a transparency and consent problem: users may request one-off analysis while the system silently retains business intelligence, which can lead to unintended long-term retention of sensitive commercial data and future cross-task leakage.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.