tycana
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill connects to the Tycana application service at
app.tycana.comvia an MCP server to provide persistent task storage and intelligence features. - [INDIRECT_PROMPT_INJECTION]: The skill features tools designed to process conversation context, which represents a potential attack surface for indirect prompt injection.
- Ingestion points: The
capturetool ingests conversation context to identify and create tasks. - Boundary markers: No explicit delimiting or boundary markers for the ingested text are defined in the skill instructions.
- Capability inventory: The skill provides full CRUD (Create, Read, Update, Delete) capabilities for tasks and project metadata through tools like
capture,update_item, anddelete_item. - Sanitization: No specific input sanitization or filtering logic is specified for the captured content.
Audit Metadata