recipe-draft-email-from-doc
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external content from a Google Document and feeds it into an outbound channel (Gmail) without safety boundaries or sanitization.
- Ingestion points:
SKILL.md(Step 1) fetches content from a Google Doc usinggws docs documents get. - Boundary markers: Absent. There are no boundary delimiters or instructions telling the model to ignore potential malicious prompts inside the fetched content.
- Capability inventory:
SKILL.md(Step 3) possesses the capability to send emails viagws gmail +send. - Sanitization: Absent. The text extracted from the document is directly embedded into the email body without validation or filtering.
Audit Metadata