ClawHub
Back to skill

Security audit

Direct Analysis

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small, disclosed Yandex Direct campaign-analysis helper, with a minor risk that broad trigger words could cause unnecessary account-data access.

Install this only if you intend to analyze Yandex Direct campaigns and are comfortable providing YANDEX_TOKEN and CLIENT_LOGIN for that purpose. Prefer explicit prompts like asking to analyze Yandex Direct campaign statistics, and avoid invoking it during casual advertising discussion.

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 (2)

Natural-Language Policy Violations

Medium
Confidence
97% confidence
Finding
All user-facing descriptive and operational language in the skill is written only in Russian, and there is no indication that the user can choose another language or locale. This creates a language policy concern because the skill appears to enforce a specific language experience without explicit opt-in or documented regional limitation.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The trigger phrases are generic enough to activate on broad, ordinary discussion about advertising, which can cause the skill to run outside the user's clear intent. Because the skill is designed to use YANDEX_TOKEN and CLIENT_LOGIN to retrieve campaign statistics, overbroad activation increases the chance of unnecessary access to sensitive advertising data or unintended external API use.

Static analysis

No suspicious patterns detected.