ClawHub
Back to skill

Security audit

Acca Tracker

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed betting-slip tracker that uses bounded scheduled score checks and does not show hidden, deceptive, or destructive behavior.

Install only if you are comfortable sharing betting-slip contents with the agent and allowing bounded background score checks. Confirm the parsed slip before tracking starts, and use "stop tracking" if you no longer want recurring updates.

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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger examples include very broad phrases like 'monitor my bet' and 'check my slip', which can plausibly appear in general sports or chat contexts and cause unintended skill invocation. In a skill that creates recurring cron jobs and performs repeated web checks, accidental activation can lead to unnecessary background activity, user confusion, and unintended processing of user-shared images or betting data.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
77% confidence
Finding

The examples present report times as "CET," which imposes a specific locale convention in the skill's natural-language output. There is no indication that the user can choose their timezone or that CET is required for a justified region-specific use case.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.