The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external Salesforce datasets, object metadata, and workload evidence. This ingestion of untrusted external content represents a surface for indirect prompt injection attacks.
Ingestion points: External datasets, object metadata, and workload evidence described in the instructions (SKILL.md).
Boundary markers: The skill instructions lack explicit directives to use delimiters or ignore embedded instructions when processing external data.
Capability inventory: The skill allows network access via WebFetch and file system modifications via Write and Edit (SKILL.md).
Sanitization: No explicit validation or sanitization steps are defined for the data ingested during the workflow.
[SAFE]: The skill references official developer documentation from Salesforce, which is a well-known service, for Bulk API 2.0 and Composite REST resources.

salesforce-core-workflow-b