sn-dimension-research
Pass
Audited by Gen Agent Trust Hub on Apr 29, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted web content which constitutes an indirect prompt injection surface. Ingestion points: search results and local project files. Boundary markers: None. Capability inventory: Writes to the local file system and updates JSON configurations. Sanitization: None.
- [DATA_EXFILTRATION]: The skill reads project-specific metadata to generate search queries for external engines, representing a legitimate but noteworthy data flow from local context to remote services.
Audit Metadata