Back to skill

Security audit

yoooclaw-world-cup-post-match-review-scene-en

Security checks for vulnerabilities and agentic risk

Overview

This skill is a sports review helper that may read local notifications for relevant fan-group discussion, but I did not find hidden execution, persistence, or data exfiltration.

Install only if you are comfortable with a sports-review skill using local notification retrieval for fan-group discussion. To reduce exposure, specify the match, time range, groups/apps, and preferred language in the request.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

YARA rule 'agent_skill_mcp_tool_poisoning_metadata': MCP/tool metadata poisoning indicators in tool schemas or skill manifests [agent_skills]

High
Category
YARA Match
Confidence
80% confidence
Finding

YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).

Content

Scanner excerpt · SKILL.md (reported line 3)May include surrounding context.

md
---
name: yoooclaw-world-cup-post-match-review-scene-en
description: Used to generate post-match reviews of World Cup football matches, and supports standardized scene input, post-match information retrieval and fan group notification extraction. It is used when the user needs to summarize the game in one sentence, how the game was played, who played the best, the hot topic after the game, or when the user explicitly requests a full review. The final answer only presents the review content without adding additional paragraphs.
---

# World Cup Post-Match Review Scene

Generate practical post-match reviews of World Cup football matches to help users

Hidden Instructions

High
Category
Prompt Injection
Confidence
60% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 133)May include surrounding context.

md
The output goal is not to "stack data", but to help users quickly understand the game, retell key nodes, and refine post-game opinions. The wording should be clear, natural, and replicable.

Generates the output type selected by the user. When the user makes multiple selections, the corresponding templates are spliced ​​in the following order: `Summary of the game in one sentence`, `How the ball was played`, `Who played the best`, `The focus of hot discussion after the game`. When the user explicitly requests `full quantity`, all 4 templates will be output in this order. In multi-select or full selection, only the top title, game date, event/stage, final score and user scenario are retained once, and subsequent templates start from the second-level title.

`Summary this game in one sentence` Output structure:

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill metadata describes activation conditions in broad, user-intent terms such as requests for summaries, analysis, best player, hot topics, or a full review, without strong gating beyond the World Cup mention. That can cause the orchestrator to invoke this skill for general sports-chat requests or unrelated match contexts, increasing the chance of incorrect tool use and unintended data retrieval.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The scene input and usage guidance define many positive triggers but almost no negative constraints, so the invocation scope remains ambiguous. In agent systems, this kind of ambiguity can lead to over-broad routing, accidental activation on partial or weak signals, and unnecessary access to retrieval/notification features.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

Forcing Chinese output by default regardless of the user's language can violate caller expectations and system language policy, especially for an English-named skill. While not a direct security exploit, it can cause policy noncompliance, misrouting, and misleading outputs in multilingual environments.

Content

No source excerpt is available for this finding.