md-report-summary
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill maintains document integrity by explicitly requiring that original image paths and data references be preserved without modification.
- [PROMPT_INJECTION]: The skill processes untrusted user drafts which creates a surface for indirect prompt injection. \n
- Ingestion points: User-provided text drafts or file content referenced in SKILL.md. \n
- Boundary markers: No explicit delimiters are used to separate user-provided content from agent instructions. \n
- Capability inventory: The skill is restricted to using WebSearch and generating Markdown text. \n
- Sanitization: Input content from drafts is processed directly without prior validation or escaping.
Audit Metadata