Back to skill

Security audit

Live Sports Scores & News

Security checks for vulnerabilities and agentic risk

Overview

This sports-score skill mostly matches its purpose, but its optional football feature asks users to pass an API key on the command line, which can expose that key in local process or command logs.

Review before installing if you plan to use the API-Football features. The general sports lookups are narrow and disclosed, but do not pass a valuable API key through the documented command-line interface unless you accept that it may appear in local logs or process metadata. Prefer a version that reads the key from a safer secret mechanism.

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

Warning
Location
scripts/sports_live.py:232
Finding

API Credential Exposed Through Command-Line Arguments

Content
View full analysis
` | Calcio live (API-Football) | `python3 ... football_live abc123` | | `football_today ` | Calcio oggi (API-Football) | `python3 ... football_today abc123` | ``` `SKILL.md:52-53`: ```markdown - Se l'utente chiede il calcio live e ha fornito una API key → usa `football_live ` - Se non è specificato lo sport per "oggi", usa `soccer` come default ``` ### Technical Analysis The documented interface requires the API-Football credential to be included directly in the command line. The script then reads that credential from `sys.argv` through `rest[0]`. Secrets supplied as process arguments may be exposed through process inspection facilities, executor or orchestration telemetry, shell history, debugging output, and retained command logs. The documentation guardrail prohibiting disclosure in the final user-facing response does not prevent disclosure through these local execution channels. The subsequent network operations at `scripts/sports_live.py:170` and `scripts/sports_live.py:194` send the credential in the `x-apisports-key` header to the fixed HTTPS endpoint `v3.football.api-sports.io`. That transmission is necessary for the declared ...[truncated 1398 chars]
Remediation
View remediation
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)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding

The skill explicitly instructs the agent to run a local Python script that calls external sports APIs, but it does not declare any tool scope such as allowed-tools or permissions for network access. This mismatch weakens policy enforcement and reviewability: an agent/runtime may permit broader execution than intended, making unauthorized network use harder to audit or constrain.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill’s natural-language description, workflow, decisions, and user-facing required response text are entirely in Italian, including an explicit canned response in Italian. There is no indication that the user can choose another language or that the skill is intentionally limited to Italian users for a justified regional purpose.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

This code file contains natural-language instructions and messages that assume Italian as the only language, including the top-level usage documentation. The policy requires flagging language or locale constraints when a skill forces a specific language without user opt-in.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The script transmits user-supplied team names to a third-party API via HTTP requests, and similar behavior occurs in other query functions. For code files, network calls that transmit user data should have some visible disclosure unless clearly warned elsewhere; this file has no such user-facing warning about sending queries to external services.

Content

No source excerpt is available for this finding.