db-architect
Pass
Audited by Gen Agent Trust Hub on Aug 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data, creating a potential surface for indirect prompt injection attacks where malicious instructions could be embedded in app ideas or PRDs.\n
- Ingestion points: The skill ingests application concepts and Product Requirement Documents provided by users to generate architectural designs (SKILL.md).\n
- Boundary markers: There are no defined delimiters or instructions to ignore embedded commands within the input text to prevent the agent from following malicious directives found in user input.\n
- Capability inventory: The skill leverages file-writing capabilities to save generated SQL schemas to the local file system at
docs/SCHEMA.mdor via artifact creation (SKILL.md).\n - Sanitization: The instructions do not include requirements for validating or sanitizing the user-provided descriptions before they are incorporated into the agent's output.
Audit Metadata