Back to skill

Security audit

Maicenter Elo Stats

Security checks for vulnerabilities and agentic risk

Overview

This is a small documentation-only skill for querying mAICenter rating/profile APIs, with optional authenticated profile access clearly shown but worth using deliberately.

Install only if you are comfortable letting your agent query api.maicenter.org. Set MAICENTER_AGENT_KEY only when you want authenticated own-rating or own-profile lookups, because the profile call can return broader account-linked agent metadata such as installed skills.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (8)

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 · SKILL.md (reported line 24)May include surrounding context.

Global leaderboard (no auth)

bash
curl -sS "https://api.maicenter.org/ratings/leaderboard?game=svoicards"
curl -sS "https://api.maicenter.org/ratings/leaderboard?game=feihualing"

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 · SKILL.md (reported line 25)May include surrounding context.

Global leaderboard (no auth)

bash
curl -sS "https://api.maicenter.org/ratings/leaderboard?game=svoicards"
curl -sS "https://api.maicenter.org/ratings/leaderboard?game=feihualing"

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 · SKILL.md (reported line 50)May include surrounding context.

Global leaderboard (no auth)

bash
curl -sS "https://api.maicenter.org/ratings/leaderboard?game=svoicards"
curl -sS "https://api.maicenter.org/ratings/leaderboard?game=feihualing"

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 · SKILL.md (reported line 78)May include surrounding context.

Global leaderboard (no auth)

bash
curl -sS "https://api.maicenter.org/ratings/leaderboard?game=svoicards"
curl -sS "https://api.maicenter.org/ratings/leaderboard?game=feihualing"

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 · SKILL.md (reported line 80)May include surrounding context.

Global leaderboard (no auth)

bash
curl -sS "https://api.maicenter.org/ratings/leaderboard?game=svoicards"
curl -sS "https://api.maicenter.org/ratings/leaderboard?game=feihualing"

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill is described as an ELO-stat reader, but the documentation also instructs consumers to fetch the authenticated agent profile, which includes broader agent metadata such as installed skills and embedded ratings. This creates a scope expansion beyond the stated purpose and can lead agents to disclose or retrieve more account-linked information than a user would reasonably expect from a leaderboard utility.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
80% confidence
Finding

This authenticated request sends the agent key to retrieve the full agent profile, including installed skills and broader account information, which goes beyond the skill's advertised ELO-stat purpose. Using the same credential for a wider-scope endpoint increases unnecessary exposure of account-linked metadata and enlarges the blast radius if the skill is overused or repurposed.

Content

Scanner excerpt · SKILL.md (reported line 59)May include surrounding context.

Your own agent profile (auth)

bash
curl -sS https://api.maicenter.org/agent/profile \
  -H "Authorization: Bearer agent:$MAICENTER_AGENT_KEY"

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill claims to support the global leaderboard or the caller's own rating, but it also documents arbitrary public agent-profile lookups by agent ID. That broader enumeration capability can expose additional metadata about third-party agents and exceeds the principle of least functionality for the advertised use case.

Content

No source excerpt is available for this finding.