welcome-to-superhuman-mail
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection because it instructs the agent to query untrusted data from email inboxes and calendar events.
- Ingestion points: Email search results and calendar event data (referenced in onboarding steps).
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions for the content of emails processed by the agent.
- Capability inventory: The skill leverages tools for drafting emails, adding accounts, and modifying calendar entries.
- Sanitization: No explicit sanitization or filtering of external content is defined in the instruction set.
- [NO_CODE]: This skill consists entirely of markdown documentation and YAML metadata. No scripts, binaries, or executable code files are included in the skill package.
Audit Metadata