discord
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill is designed to read messages and search history on Discord, which allows untrusted external data to enter the agent's context. * Ingestion points: The 'read' and 'search' actions in SKILL.md ingest external message content. * Boundary markers: There are no explicit boundary markers or instructions to ignore embedded commands within the ingested content. * Capability inventory: The agent can perform 'send', 'react', 'delete', 'poll', and 'pin' actions through the message tool. * Sanitization: No sanitization or filtering of external content is described.
- [Prompt Injection] (SAFE): No instructions attempting to bypass safety filters or override the system prompt were found.
- [Data Exposure & Exfiltration] (SAFE): No hardcoded credentials or sensitive file paths were detected; the skill correctly requires a configuration token for authentication.
- [Unverifiable Dependencies] (SAFE): No external packages or remote execution patterns were found.
Audit Metadata