deal-advance-gap
Pass
Audited by Gen Agent Trust Hub on Nov 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from various untrusted sources, which could potentially contain malicious instructions intended to manipulate the agent's analysis or behavior.
- Ingestion points: The skill retrieves data from Salesforce Opportunity fields, email exchanges, Slack threads, and document transcripts (identified in sections 2b and 2c).
- Boundary markers: The instructions lack specific requirements for using delimiters or boundary markers when the agent incorporates external data into its context for analysis.
- Capability inventory: The skill utilizes Salesforce integration tools (
dispatch_readonly,dispatch) and relies on connectors for email, documents, and Slack to gather evidence. It also uses a widget display tool for output. - Sanitization: There is no evidence of content sanitization, escaping, or validation mentioned in the instructions for data ingested from the various external integrations.
Audit Metadata