revenue-cloud-pcm
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion and processing of master data from external Salesforce organizations, creating a surface for indirect prompt injection if descriptions, names, or attribute labels in the source data contain instructions designed to influence the agent.\n
- Ingestion points: Master data and metadata retrieved via the Salesforce CLI in scripts such as
scripts/check-orphans.sh,scripts/list-catalogs.sh, andscripts/query-product-tree.sh.\n - Boundary markers: The skill does not implement delimiters or explicit 'ignore' instructions for data retrieved from external orgs.\n
- Capability inventory: The skill executes read-only shell commands using
sfandjqfor metadata inspection.\n - Sanitization: No evidence of validation or sanitization of text-based record fields is present in the utility scripts.
Audit Metadata