using-salesforce-archive
Pass
Audited by Gen Agent Trust Hub on Jun 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill operates within the Salesforce platform ecosystem, using documented endpoints under
/platform/data-resilience/archive/and standard SOQL for theArchiveActivityentity.\n- [SAFE]: It emphasizes the necessity of granular user permissions (e.g.,ViewSearchPage,Rtbf) for different operations, ensuring alignment with Salesforce's security model.\n- [PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it retrieves and processes data from external archived records.\n - Ingestion points: Data is retrieved from the Salesforce Archive via
search-archived-recordsand next-page operations defined inreferences/connect-api-operations.md.\n - Boundary markers: The instructions do not define specific delimiters or warnings to prevent the agent from obeying instructions embedded within the retrieved record content.\n
- Capability inventory: The skill is capable of performing state-changing operations such as unarchiving, RTBF erasure, and PII masking via the Connect API.\n
- Sanitization: The documentation indicates that some response fields (e.g.,
recordsJson) are HTML-entity-encoded, which provides a layer of protection against certain injection payloads.
Audit Metadata