discord-get-messages
Pass
Audited by Gen Agent Trust Hub on Apr 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use standard tools like curl, jq, and tac to interact with the Discord API and process the results.
- [DATA_EXFILTRATION]: The skill transmits the DISCORD_BOT_TOKEN environment variable to the official Discord API at discord.com, which is the intended behavior for this well-known service.
- [PROMPT_INJECTION]: The skill retrieves message content from external Discord channels, creating a surface for indirect prompt injection where untrusted content could influence agent behavior.
- Ingestion points: Message content retrieved via API requests to discord.com.
- Boundary markers: No explicit delimiters or instructions to treat data as untrusted are provided.
- Capability inventory: Shell command execution via curl and jq.
- Sanitization: No sanitization of message content is mentioned.
Audit Metadata