Security audit

Acca Tracker

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed betting-slip tracker that uses live-score lookups and bounded scheduled checks, with no evidence of deception, exfiltration, or destructive behavior.

Before installing, be aware that tracking creates a recurring job and may leave betting-slip reports in local cron output. Use it only for score monitoring and rough cash-out estimates, not as financial advice, and confirm the parsed slip carefully before starting tracking.

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

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands

Findings (5)

Tp4

High

Category: MCP Tool Poisoning
Confidence: 95% confidence
Finding: The declared description promises a betting-slip tracker that can ingest slip photo/text, monitor relevant matches over time, and compute betting-specific status such as acca health and cash-out context. The supplied code only implements a generic live score fetcher for specified date/sport inputs, plus optional team filtering. While live score retrieval for football/basketball/tennis is related support functionality, the core advertised capabilities—slip parsing, accumulator tracking, scheduled polling, and betting-context reporting—are absent from this code chunk. Therefore the description materially overstates what this code actually does.
Content: No source excerpt is available for this finding.

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 90% confidence
Finding: The skill explicitly instructs the agent to use terminal commands and recurring cron jobs, but it does not declare any tool restrictions or allowed-tools/permissions metadata. This makes the operational scope opaque and increases the chance the skill is invoked with broader shell capability than users or platform policy expect, which is risky because it can create persistent jobs and execute local scripts.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger phrases are broad enough to match ordinary conversation such as 'check my slip' or 'monitor my bet', which can cause accidental activation. In this skill, accidental activation is more dangerous than usual because invocation can lead to recurring cron creation, web lookups, local report generation, and ongoing monitoring without the user fully understanding the side effects.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The skill creates a repeating cron job and stores generated reports locally, but these persistence and storage side effects are not prominently disclosed before use. Hidden persistence is security-relevant because it can continue running after the user’s immediate request, consume resources, and retain potentially sensitive betting data or delivery metadata on disk.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

Low

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The package description says the skill tracks only 'football accumulator betting slips' and reports overall acca health, but the higher-level skill manifest context describes broader multi-sport support and cash-out context. This is a semantic scope mismatch in the skill's declared behavior, even though no executable code is present in this file.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.