The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests data from external files, creating a potential vector for indirect prompt injection attacks.
Ingestion points: Data templates in assets/csv/ and assets/json/, as well as user-provided Apex scripts intended for execution via sf apex run.
Boundary markers: The instructions do not define specific delimiters or instructions for the agent to ignore potentially malicious instructions embedded within the record data.
Capability inventory: The skill possesses significant capabilities, including creating, updating, and deleting Salesforce records, and executing arbitrary anonymous Apex code in the target environment.
Sanitization: The skill emphasizes schema and picklist validation, but it lacks specific mechanisms to sanitize or filter text content against instructions directed at the agent.

platform-data-manage