Gr Community Ambassador

• Outcome: Pass
• Latest audit: Jun 19, 2026 at 12:41 PM UTC
• Version:
  1.2.0

Overview

This is a markdown playbook for community and ambassador program operations, with no code, credentials, persistence, or hidden execution behavior.

Install this if you want a Chinese-first ambassador program playbook. Be aware that it may activate for broad community-growth prompts, and validate any marketing tactics such as social monitoring, reposting, and incentive programs against your community norms and platform rules.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Vague Triggers

Medium

• Confidence: 95% confidence
• Finding: The trigger list contains broad, generic phrases such as "community building," "community management," and "user retention" that can match many ordinary user requests outside the narrow scope of this skill. This can cause the agent to invoke the skill in unintended contexts, overriding more appropriate behavior and increasing the chance of irrelevant, manipulative, or low-quality guidance being injected into conversations.

Natural-Language Policy Violations

Medium

• Confidence: 84% confidence
• Finding: The skill body defaults to Chinese presentation while only linking to other languages, without a clear mechanism to detect or request the user's preferred language before delivering content. In practice, this can lead to misinterpretation of guidance, reduced transparency, and accidental misuse when the agent activates the skill for users expecting another language.

VirusTotal

62/62 vendors flagged this skill as clean.