discord
Pass
Audited by Gen Agent Trust Hub on Aug 1, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exposes a surface for indirect prompt injection attacks.
- Ingestion points: Untrusted content enters the agent's context through the
readandsearchactions, which fetch data from external Discord channels and guilds. - Boundary markers: There are no instructions for using delimiters or boundary markers to isolate data retrieved from Discord from the agent's core instructions.
- Capability inventory: The agent has significant capabilities including sending and deleting messages, creating threads, and managing polls. The
mediaparameter supportsfile:///URIs, which could potentially be used to attach local system files if the agent is manipulated into doing so via external content. - Sanitization: The instructions lack guidance on sanitizing or validating the content of messages retrieved from Discord before processing them.
Audit Metadata