discord-chat
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its message-reading capabilities.\n
- Ingestion points: External data is ingested from Discord channels via the read and search actions documented in SKILL.md and references/SEARCH.md.\n
- Boundary markers: The documentation does not define delimiters or instructions for the agent to ignore embedded commands within the retrieved Discord content.\n
- Capability inventory: The agent possesses extensive capabilities including sending, editing, and deleting messages, as well as managing channels and categories across different server IDs.\n
- Sanitization: There is no mention of sanitization or validation of the retrieved Discord message content before it is processed by the agent.
Audit Metadata