code-design-api
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted external data which creates a surface for indirect prompt injection.
- Ingestion points: The skill fetches web content via 'WebFetch' in 'SKILL.md' and interpolates user-provided requirements and protocols into sub-agent tasks in 'SUBAGENT.md'.
- Boundary markers: No delimiters, markers, or explicit instructions to ignore nested commands are provided for the external data or interpolated variables.
- Capability inventory: The skill is focused on text and specification generation and does not exhibit direct file system access, subprocess execution, or sensitive network capabilities in the provided source.
- Sanitization: There is no evidence of input validation, escaping, or content sanitization before processing external data.
- [NO_CODE]: No executable code, scripts, or binaries are shipped with the skill.
Audit Metadata