synthesis-link-research
Pass
Audited by Gen Agent Trust Hub on Apr 22, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists of natural language instructions for performing link research and formatting the output as HTML. No malicious patterns, obfuscation, or unauthorized commands were detected.
- [PROMPT_INJECTION]: The skill identifies a potential surface for indirect prompt injection via user-provided content. 1. Ingestion points: User-provided text for entity extraction and research. 2. Boundary markers: Absent from the instructions. 3. Capability inventory: Implicit use of search and browsing tools. 4. Sanitization: None described.
Audit Metadata