omnistudio-dependencies-analyze

Pass

Audited by Gen Agent Trust Hub on Oct 7, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill identifies an attack surface where it ingests and processes metadata from Salesforce records.
  • Ingestion points: Metadata fields such as PropertySetConfig, DataSourceConfig, and Definition are retrieved from Salesforce objects using the sf CLI.
  • Boundary markers: The instructions do not explicitly require delimiters or warnings to disregard instructions that might be embedded in the retrieved JSON metadata.
  • Capability inventory: The skill uses sf data query for metadata retrieval and sf api request rest for interaction with Salesforce APIs.
  • Sanitization: Technical dependencies are extracted by parsing JSON structures without specific sanitization of the string content for embedded prompt instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 7, 2026, 07:06 PM