low-level-design
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it is designed to ingest and process untrusted data from user specifications and existing project source code. It possesses the capability to read project files for analysis and write design documentation or drafts back to the project's file system. The instructions do not explicitly mandate the use of boundary markers or sanitization techniques when processing this external content.\n
- Ingestion points: Project source code, user-provided specifications, and existing design documents (SKILL.md).\n
- Boundary markers: Not specified in the instructions.\n
- Capability inventory: File system read access for code analysis and file system write access for documentation updates (SKILL.md).\n
- Sanitization: No explicit sanitization or validation of ingested content is mentioned.\n- [SAFE]: The skill's primary function is to provide architectural guidance based on established principles such as SOLID, KISS, and DRY. All referenced external materials are from well-known educational sources. No evidence of command execution, data exfiltration, obfuscation, or persistence mechanisms was found.
Audit Metadata