free-design-resources
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied information about design tools and licensing terms to generate structured artifacts such as CSV, SQL, and JSON. Although this creates an ingestion surface for untrusted data, the instructions provide strong guidance to prevent accidental execution or misinterpretation of embedded instructions by requiring explicit verification and using 'Unverified' as a default state.\n
- Ingestion points: User replies describing tool requirements and licenses (SKILL.md, Step 2).\n
- Boundary markers: The skill instructs the agent to 'keep prose outside the data' and uses a structured field list to constrain outputs.\n
- Capability inventory: Generation of SQL DDL, JSON schema, and CSV text. The skill does not possess file-write or network execution capabilities.\n
- Sanitization: Instructions emphasize recording 'Unverified' for unknown terms and explicitly forbid inventing data.\n- [EXTERNAL_DOWNLOADS]: The documentation references an external GitHub repository (github.com/WHOISABHISHEKADHIKARI/sme-ops-system-builder) for supporting materials and prerequisites. This repository belongs to the skill's author and is used for reference purposes rather than automated script execution.
Audit Metadata