platform-lightning-app-coordinate

Pass

Audited by Gen Agent Trust Hub on Jun 26, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill follows established architectural patterns for Salesforce metadata generation, relying on specific internal tools and sub-skills from the author.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted natural language input from users to generate application structure.
  • Ingestion points: User natural language requests are parsed in STEP 1 to identify objects, fields, and logic.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are defined for the input string within this orchestration level.
  • Capability inventory: The skill coordinates file-writing operations across multiple sub-skills to create metadata files and deployment manifests on the local filesystem.
  • Sanitization: The skill includes validation steps for Salesforce naming conventions, reserved words, and relationship limits to ensure cross-component integrity.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 26, 2026, 12:50 PM
Security Audit — agent-trust-hub — platform-lightning-app-coordinate