discord-admin-py

Pass

Audited by Gen Agent Trust Hub on Sep 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill interacts with the Discord API to manage messages and server metadata, establishing a surface for indirect prompt injection from external Discord users. Ingestion points: Untrusted data is retrieved from Discord API endpoints, such as message lists and invite metadata. Boundary markers: The instructions and code examples do not specify the use of delimiters or 'ignore' instructions for external content. Capability inventory: The skill provides capabilities for message manipulation, role assignment, and member moderation. Sanitization: No sanitization of external Discord data is present in the skill definitions.
  • [SAFE]: No malicious patterns, such as obfuscation, credential exfiltration, or unauthorized command execution, were identified in the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 28, 2026, 06:50 PM