discord
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection via the processing of external Discord data.
- Ingestion points: The skill facilitates data ingestion from untrusted external sources through the 'read' and 'search' actions in SKILL.md.
- Boundary markers: There are no instructions or delimiters defined to separate external message content from system instructions or to warn the agent about embedded commands.
- Capability inventory: The 'message' tool provides write-access capabilities including sending messages, deleting content, managing threads, and setting presence, which could be misused if an injection is successful.
- Sanitization: No sanitization, filtering, or validation of the ingested Discord content is specified before the data is processed by the agent.
Audit Metadata