The Agent Skills Directory

[SAFE]: No security vulnerabilities or malicious patterns were detected. The skill provides standard developer tooling for Salesforce data lifecycle management.
[COMMAND_EXECUTION]: The skill executes official Salesforce CLI (sf) commands to manage records and run anonymous Apex. This behavior is consistent with the skill's primary purpose of Salesforce org management.
[PROMPT_INJECTION]: The skill processes data from local CSV, JSON, and Apex templates, which constitutes a potential surface for indirect prompt injection. However, this risk is mitigated by the skill's 'describe-first' workflow and the inclusion of specialized validation scripts.
Ingestion points: Template files located in assets/csv/, assets/json/, and assets/factories/.
Capability inventory: Data manipulation via sf data and code execution via sf apex run.
Boundary markers: Detailed documentation and metadata guide the agent in distinguishing instructions from data templates.
Sanitization: Employs dedicated Python scripts (scripts/soql_validator.py and scripts/validate_data_operation.py) to validate SOQL syntax, bulk safety, and data integrity before execution.

platform-data-manage