chatcut-connect
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns or security vulnerabilities were detected. The skill follows security best practices by explicitly instructing the agent not to expose sensitive session tokens (editor-boot-token) or internal handoff URLs in the user-facing output.
- [INDIRECT_PROMPT_INJECTION]: The skill processes project metadata returned by external tools, which represents a standard indirect injection surface.
- Ingestion points: Project names, IDs, and URLs returned by the
list_projectsMCP tool. - Boundary markers: No specific delimiters or boundary warnings are used when presenting project data in the output table.
- Capability inventory: Includes tool calls for authentication and project listing, as well as delegation to editor handoff skills.
- Sanitization: The skill relies on the underlying platform and the specific instructions to use 'clean' links, but does not implement explicit validation of the project data strings.
Audit Metadata