x-dm
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill includes an 'Inbox triage' feature that processes external data (DM content and message requests) provided by the user. While this creates a potential attack surface for indirect prompt injection, the skill's capabilities are limited to text categorization and drafting. It does not possess any dangerous capabilities such as file system writes, network exfiltration, or shell execution that could be exploited by embedded instructions.
- Ingestion points: User-pasted DM content processed in the 'Inbox triage' section.
- Boundary markers: Not explicitly defined in instructions.
- Capability inventory: Limited to drafting text and categorizing inputs; no dangerous tools are utilized.
- Sanitization: Not specified.
- [SAFE]: The skill follows security best practices by explicitly prohibiting automated or bulk messaging ('Never send the message', 'Never send bulk or automated DMs'). It relies on the user to manually review and send all communications, maintaining human-in-the-loop control.
Audit Metadata