connect-ai-salesforce
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of data from Salesforce objects, which are untrusted external sources capable of containing malicious instructions.\n- Ingestion points: The skill provides guidance for fetching data from tables such as Lead, Contact, and Case using the queryData tool, as detailed in SKILL.md.\n- Boundary markers: The instructions do not specify the use of data delimiters or include explicit instructions for the agent to ignore potentially malicious content embedded within the retrieved Salesforce records.\n- Capability inventory: SKILL.md documents the use of significant capabilities, including SQL write operations (INSERT, UPDATE) and stored procedures like ConvertLead and Merge, which could be targeted by an injection attack.\n- Sanitization: There are no recommendations or requirements provided in the instructions for sanitizing or validating external data before the agent processes it.
Audit Metadata