senior-backend
Pass
Audited by Gen Agent Trust Hub on Nov 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data sources via
api_scaffolder.py(OpenAPI specs) anddatabase_migration_tool.py(SQL schemas). A maliciously crafted specification could potentially contain instructions intended to override agent behavior or inject insecure patterns into the generated boilerplate code. - Ingestion points: The agent is instructed to read and process external schema and API specification files, such as those in the
assets/directory or provided by the user. - Boundary markers: The instructions do not define clear delimiters or "ignore embedded instructions" warnings for the agent when processing these external data formats.
- Capability inventory: The skill possesses the capability to write files to the local system (generated routes, types, and migrations) and execute network operations (via
api_load_tester.py). - Sanitization: The provided Python scripts perform structural parsing but lack explicit sanitization mechanisms to prevent the interpolation of malicious instructions or payload-bearing content into generated TypeScript/JavaScript files.
Audit Metadata