discord
Pass
Audited by Gen Agent Trust Hub on Jun 23, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill facilitates reading external data from Discord, creating a surface for indirect prompt injection.
- Ingestion points: The
readandsearchactions inSKILL.mdallow the agent to ingest untrusted content from Discord channels and user messages. - Boundary markers: There are no instructions for the agent to use specific delimiters or to ignore potential instructions embedded in the retrieved Discord content.
- Capability inventory: The agent has access to the
messagetool with multiple Discord-specific actions, includingsend,edit,delete,react,poll,pin,thread-create, andset-presence. - Sanitization: The skill does not provide any mechanisms for sanitizing or validating the content retrieved from external Discord sources.
Audit Metadata