backend-to-frontend-handoff-docs
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted local data (source code, DTOs, and task descriptions) to generate documentation, which creates a vulnerability surface for embedded instructions to influence the agent.
- Ingestion points: The skill reads local backend code, including endpoints, controllers, services, DTOs, and validation logic, as well as business context provided in task descriptions.
- Boundary markers: While the skill utilizes a structured markdown template for output, it lacks explicit instructions to treat source code content as data only or to ignore any natural language instructions found within code comments.
- Capability inventory: The skill has the capability to write files to the
.claude/docs/ai/directory on the local filesystem. - Sanitization: There is no evidence of sanitization or filtering of the extracted content from source files before it is interpolated into the final documentation output.
Audit Metadata