recipe-draft-email-from-doc
Pass
Audited by Gen Agent Trust Hub on Mar 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
gwscommand-line tool to retrieve document data and send emails. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from an external document and uses it in a subsequent action without sanitization.
- Ingestion points: Document content is retrieved via
gws docs documents getinSKILL.md. - Boundary markers: No delimiters or safety instructions are used to separate the document content from the agent's logic.
- Capability inventory: The skill has the capability to send emails using
gws gmail +sendinSKILL.md. - Sanitization: There is no evidence of validation or escaping for the document body content before it is drafted as an email body.
Audit Metadata