discord
Pass
Audited by Gen Agent Trust Hub on May 18, 2026
Risk Level: SAFEPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of content from Discord, which may contain instructions from untrusted external users. * Ingestion points:
readandsearchactions inSKILL.md. * Boundary markers: Absent. * Capability inventory:send,edit,delete,set-presence, and file access viamediainSKILL.md. * Sanitization: Absent. - [DATA_EXPOSURE_AND_EXFILTRATION]: The skill documents the ability to read files from the local filesystem and upload them to Discord. * Evidence: The
sendaction inSKILL.mdincludes amediafield using thefile://protocol. This allows the agent to read files and transmit them to external Discord channels.
Audit Metadata