email-writer
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input to generate email drafts.
- Ingestion points: User descriptions and requirements for the email content (e.g., recipient, purpose, urgency).
- Boundary markers: Absent; user input is directly used by the agent to draft the response without explicit delimiters or "ignore embedded instructions" warnings.
- Capability inventory: None; the skill does not use any tools or perform file-system, network, or subprocess operations.
- Sanitization: Absent; the instructions do not specify any validation or escaping of the user-provided content.
Audit Metadata