discord-admin-py
Pass
Audited by Gen Agent Trust Hub on Feb 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection (LOW): The skill processes data from an untrusted external source (Discord) which could contain malicious instructions that influence the agent's behavior.
- Ingestion points: Data returned from the Discord API, such as
invite_code, message contents, and member metadata used in theAppmethods. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the provided implementation examples.
- Capability inventory: The skill possesses significant administrative capabilities, including the ability to ban/kick members, manage roles, create channels, and manage webhooks.
- Sanitization: There is no evidence of sanitization or validation of the data retrieved from the Discord API before it is processed or returned to the agent context.
Audit Metadata