inbox-sweep
Pass
Audited by Gen Agent Trust Hub on Nov 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external unread emails and uses it to classify messages and draft replies, creating a potential surface for indirect instructions to influence agent behavior.
- Ingestion points: External unread emails from non-internal domains are searched and read in Step 1 and Step 3.
- Boundary markers: The instructions lack explicit delimiters or instructions to ignore embedded commands when interpolating email thread content into drafting or classification prompts.
- Capability inventory: The skill utilizes
dispatch_readonlyanddispatchfor Salesforce operations, drafts email content based on thread context, and invokesdisplay_widgetfor UI presentation. - Sanitization: There is no documented mechanism for filtering, escaping, or validating the content of the external email threads before they are processed by the agent.
Audit Metadata