ClawHub
Back to skill

Security audit

FootballBin Predictions

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small, disclosed FootballBin API client that sends soccer prediction query parameters to a public endpoint and does not show hidden local access, persistence, or credential handling.

Before installing, understand that this skill contacts a third-party FootballBin service and sends the soccer league, matchweek, and team filters you request. It does not appear to collect local data or credentials, but users who avoid external sports prediction APIs should not install it.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

MCP Config Access

High
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill accesses MCP server configuration files (mcp.json). MCP configs contain server URLs, authentication tokens, and tool definitions — reading them allows the skill to discover and potentially abuse other tool integrations.

Content

Scanner excerpt · scripts/footballbin.sh (reported line 19)May include surrounding context.

sh
Usage: footballbin.sh <command> [options]

Commands:
  tools                              List available MCP tools
  predictions <league> [matchweek]   Get match predictions

Options for predictions:

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding

The skill advertises shell-based execution requirements via metadata (curl, jq, and scripts/*) but does not declare an explicit tool scope such as permissions or allowed-tools. That creates a gap between documented capabilities and enforceable restrictions, increasing the risk that an agent runtime grants broader shell access than intended or executes local scripts without a clear least-privilege boundary.

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/footballbin.sh (reported line 12)May include surrounding context.

sh
#   Data sent: league name, matchweek number, team name filters (no PII)
#   Software installation: none

MCP_ENDPOINT="https://api.footballbin.achaninc.net/mcp"

usage() {
    cat <<'EOF'

External Transmission

Medium
Category
Data Exfiltration
Confidence
70% 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/footballbin.sh (reported line 40)May include surrounding context.

sh
# Call the MCP endpoint with a JSON-RPC payload
mcp_call() {
    local payload="$1"
    curl --fail --show-error --silent --max-time 20 -X POST "$MCP_ENDPOINT" \
        -H "Content-Type: application/json" \
        -d "$payload"
}

Static analysis

No suspicious patterns detected.