base44-platform-platform
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to ingest and evaluate external data to identify the framework and configuration of the current project.
- Ingestion points: The agent is instructed to read project-specific files (e.g.,
src/routes/__root.*,app/_layout.*) and process API data fromGET /api/apps/{app_id}/agent-profile. - Boundary markers: No explicit instructions are provided to use delimiters or ignore embedded instructions within the external content being processed.
- Capability inventory: The agent is granted capabilities to create, edit, and delete files, and to execute platform API calls via the
execute_apitool. - Sanitization: There are no instructions for validating or sanitizing the information gathered from project files or API responses before it influences subsequent agent operations.
Audit Metadata