Back to skill

Security audit

World Cup 2026 DEEP analysis

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed football analytics skill that uses local model files plus optional sports and odds APIs, with some manageable credential and over-triggering caveats.

Install only if you want a Chinese-language football prediction and odds-analysis helper. Use optional API keys with normal caution, especially ODDS_API_KEY because the provider code puts it in request URLs and an in-memory cache. Expect calibration commands to modify the skill's local rating, team-stat, schedule, and log files, with backups created for data updates.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Note
Location
scripts/odds_provider.py:43
Finding

API Key Exposed in Request URL and In-Memory Cache Key

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (17)

Tainted flow: 'req' from os.getenv (line 192, credential/environment) → urllib.request.urlopen (network output)

Critical
Category
Data Flow
Confidence
90% confidence
Finding

Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.

Content

Scanner excerpt · scripts/calibrate.py (reported line 196)May include surrounding context.

python
f"{FOOTBALL_DATA_URL}?{params}",
        headers={"X-Auth-Token": api_key, "User-Agent": "wc2026-skill/2.1"})
    try:
        with urllib.request.urlopen(req, timeout=30) as resp:
            data = json.loads(resp.read().decode("utf-8"))
    except urllib.error.HTTPError as e:
        raise Exception(f"football-data.org 请求失败 {e.code}: {e.read()[:200]}")

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

The file claims a rich prediction engine and specific statistical methods, but the described behavior also includes undeclared data mutation and logging while lacking evidence of the promised implementation. This mismatch is dangerous because reviewers and users may grant trust and permissions based on the stated benign analytics purpose, while the actual capability surface includes persistent state changes and external-data ingestion that can affect integrity, reproducibility, and agent behavior.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding

The skill advertises and instructs use of environment secrets, network access, and local file reads/writes, but it does not declare any explicit tool scope or allowed-tools policy. That creates an over-privileged execution posture where the agent may invoke broader capabilities than reviewers or users expect, especially since the skill writes calibration data, logs, and group files and can pull remote data via search/API.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

L003 将触发条件扩展到“当用户要求分析足球比赛、预测结果…或提到足球/世界杯/欧冠/英超/五大联赛等赛事分析时使用”。其中“提到足球/世界杯/欧冠/英超”等表述范围很广,缺少明确边界或排除条件,容易与普通体育聊天、新闻讨论或泛泛提及赛事的对话重叠。

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

L003 的整体描述完全以中文定义技能用途与交互范围,且未说明可根据用户偏好切换语言。按规则,若技能对语言/locale 有隐含强制要求而未提供选择或明确正当理由,属于自然语言政策问题。

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

This manifest-style JSON file encodes all country/team identifiers exclusively in Chinese, which imposes a specific language/locale on downstream users or components. Under the policy, forcing a specific language without user choice or documented regional justification is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

Several user-facing values are hard-coded in Chinese, including the advance rule, knockout round names, and host country names. Because this file does not document that the skill is region-specific or offer a language choice, it appears to impose a locale/language preference without user opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file contains user-facing natural language exclusively in Chinese, and there is no indication that users can opt into another language or that the skill is intentionally limited to a Chinese-speaking or region-specific audience. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/calibrate.py (reported line 166)May include surrounding context.

python
# ----------------------------------------------------
# API backup: football-data.org (搜索不可用时的兜底)
# ----------------------------------------------------
FOOTBALL_DATA_URL = "https://api.football-data.org/v4/competitions/WC/matches"
HOST_VENUES_HOME = True  # API 的 homeTeam 即东道主主场判断依据

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The module description, runtime messages, and comments are all in Chinese, and there is no indication that users can opt into another language or that the skill is intentionally limited to a Chinese-speaking audience. This can violate language/locale policy when a skill imposes a language without explicit opt-in or justification.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/odds_provider.py (reported line 21)May include surrounding context.

python
import urllib.request
from typing import Dict, List, Optional

BASE_URL = "https://api.the-odds-api.com/v4"
SPORT_MATCH = "soccer_fifa_world_cup"          # 比赛盘 (h2h)
SPORT_WINNER = "soccer_fifa_world_cup_winner"  # 夺冠盘 (outrights)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The code appends the API key to the request query string, which is commonly captured in logs, proxies, browser/debug tooling, and upstream monitoring systems. Even though the destination uses HTTPS and this is a third-party API convention, putting secrets in URLs increases accidental credential exposure risk beyond the immediate application boundary.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The module description, comments, docstrings, and CLI output are written entirely in Chinese, which constitutes a language-specific natural-language policy constraint embedded in the skill. The file does not indicate that Chinese is optional, user-selectable, or required for a region-specific purpose, so it may violate the rule against forcing a specific language without user opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The natural-language descriptions for all correction factors are written entirely in Chinese, which imposes a specific language/locale in this skill data. There is no indication that users can choose another language or that the file is intentionally limited to a Chinese-only regional context, so this fits the language/locale policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

This manifest-style JSON file encodes all country names exclusively in Chinese, which imposes a specific language/locale in the skill data. Under the policy, language constraints should either offer user choice or be explicitly documented as justified for a region-specific use case, neither of which is evident in this file.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

This JSON maps English team names exclusively to Chinese names, and the note states the purpose is to translate API team names into local data keys. Because the file hard-codes one locale without any visible opt-in or explanation that the skill is intentionally Chinese-only, it presents a natural-language locale policy concern under the stated rules.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

This JSON manifest-like file contains a natural-language instruction about how an agent should populate the groups data, but it does not specify when this behavior should or should not be triggered. The wording describes an action flow broadly rather than constraining invocation context, which could lead to unintended use in adjacent contexts.

Content

No source excerpt is available for this finding.