discord
Pass
Audited by Gen Agent Trust Hub on Feb 26, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: Indirect Prompt Injection Surface
- Ingestion points: The skill instructs the agent to fetch and review recent messages from the Discord server's 'general' channel (SKILL.md).
- Boundary markers: No specific delimiters or instructions to ignore commands embedded within the retrieved Discord messages are defined in the skill instructions.
- Capability inventory: The skill provides instructions for using powerful tools including posting messages, creating events, and performing moderation actions such as timing out, kicking, or banning members.
- Sanitization: There is no evidence of content sanitization or validation for the messages processed from the external source.
- [NO_CODE]: The analyzed skill consists solely of markdown instructions and server metadata. It does not contain any scripts, binaries, or package dependency files.
Audit Metadata