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
Risk Level
SAFE
Analyzed
Feb 26, 2026, 10:57 PM