Back to skill

Security audit

World Cup Prophet

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed World Cup information and prediction helper that uses local static data and UI cards, with no evidence of credential access, exfiltration, destructive behavior, or persistence.

Install this if you want a Chinese-language World Cup helper with card-based output and entertainment predictions. Be aware that broad sports terms may route to this skill unless the agent asks for clarification, and prediction or fortune features should not be treated as factual forecasts.

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
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (11)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The trigger phrases are broad and generic for sports conversations, which can cause the skill to activate outside the user's intended context. This can misroute user requests, override more appropriate skills, or cause the agent to call prediction or sports APIs when the user was asking a general question not specifically about this World Cup skill.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The routing rules map very common terms like 'matches', 'results', and 'champion' directly to this skill without requiring clear domain signals. In a multi-skill agent, this increases the risk of unintended activation and incorrect tool use, which can degrade integrity of responses and expose unrelated conversations to this skill's logic.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The string instructs the system to present the bracket to the user and prohibits plain-text listing, but it does so entirely in Chinese and assumes a Chinese-language interaction model. This creates a natural-language locale policy issue because the skill does not offer a language choice or document that it is intentionally limited to a Chinese-only audience.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The user-facing string and embedded instruction are written only in Chinese and include a prescriptive display constraint, which effectively imposes a specific language/locale behavior without offering user choice. The policy explicitly flags language or locale constraints when they are forced without opt-in or justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The user-facing instruction and messages are entirely in Chinese, including a directive for how results should be presented, with no indication that the skill is limited to Chinese-speaking users or that language choice is configurable. This can violate language/locale policy when a skill imposes a specific language without user opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The file's user-facing strings are consistently hardcoded in Chinese, including error and instruction text. This creates a language/locale policy concern because the skill does not provide any user opt-in or fallback language behavior, and no region-specific justification is present in the file.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

Multiple user-facing strings and behavioral instructions are written exclusively in Chinese, including guidance such as asking follow-up questions and presenting results. The file does not offer any language choice or indicate that Chinese-only output is a documented, justified locale constraint, which can violate language/locale policy requirements.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The returned text is entirely in Chinese and includes behavioral instructions for how results should be presented, with no indication that the user can choose another language or locale. This is a natural-language policy issue because it imposes a specific language by default rather than offering localization or documenting a justified locale constraint.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The string instructs that the next response must include a specific Chinese disclaimer and forbids a plain-text presentation, effectively forcing Chinese-language output regardless of the user's preferred language. This is a natural-language policy concern because the file provides no opt-in, locale selection, or documented justification for restricting language.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The API descriptions, invocation conditions, and parameter guidance are written entirely in Chinese throughout the manifest, which effectively constrains use to a specific language/locale. There is no indication that users may interact in another language or that this Chinese-only behavior is an intentional, documented regional restriction.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
96% confidence
Finding

This JavaScript file contains natural-language comments and user-facing data entirely in Chinese, including the skill identity and descriptive text, with no indication that language is selectable or limited to a China-specific deployment. That can violate a language/locale policy when a skill implicitly enforces one language without user opt-in.

Content

No source excerpt is available for this finding.