endpoint-scaffold
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill serves a legitimate developer productivity purpose by automating the creation of validated and authorized backend endpoints. It does not contain any suspicious commands, obfuscated content, or unauthorized network activity.
- [INDIRECT_PROMPT_INJECTION]: The skill has a standard attack surface for AI-assisted code generation as it takes user-defined intents and contracts to produce source code.
- Ingestion points:
SKILL.md(Inputs section: Endpoint intent, Contract surface, Authorization expectation, Error expectations). - Boundary markers: The skill does not define specific prompt delimiters or instructions to ignore embedded instructions in user input.
- Capability inventory: The agent is expected to perform file-write operations to create or update endpoint handlers, routers, validation schemas, and test files.
- Sanitization: No explicit sanitization or filtering of user input is mentioned, relying on the underlying agent's standard guardrails.
Audit Metadata