platform-lightning-app-coordinate
Pass
Audited by Gen Agent Trust Hub on Aug 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes natural language descriptions to generate Salesforce metadata and orchestrate build plans, creating a surface for indirect prompt injection where malicious instructions could be embedded in the user's description.
- Ingestion points: User-provided natural language requests are parsed in 'STEP 1: Requirements Analysis & Planning' to extract business entities and logic.
- Boundary markers: The instructions do not define explicit delimiters (e.g., XML tags or special markers) or specific instructions for the agent to treat the user description strictly as data.
- Capability inventory: The skill writes multiple XML metadata files to the local file system (SFDX project structure) and utilizes MCP tools like 'execute_metadata_action' to modify the Salesforce environment.
- Sanitization: There is no evidence of specific sanitization, escaping, or filtering logic applied to the natural language input before it is used to drive the generation process.
Audit Metadata