markbuildbrand-foundation-docs
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is composed of markdown-based templates and instructional prompts. No malicious logic, obfuscation, or unauthorized data access was found.- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it processes external links and screenshots provided by the user.
- Ingestion points: User-provided 'Product Link' and 'Screenshot' in SKILL.md.
- Boundary markers: None used to isolate external content from agent instructions.
- Capability inventory: Utilization of a 'Deep Research' tool for analyzing the provided inputs.
- Sanitization: No input validation or sanitization logic is present.
Audit Metadata