attio-install-auth
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes local project files to configure authentication, which presents a surface where data in the repository could influence agent behavior.\n
- Ingestion points: Local authentication wrappers and configuration files in the specified repository path (accessed via
Read,Glob, andGrep).\n - Boundary markers: The instructions lack explicit delimiters to separate file content from instructions.\n
- Capability inventory: The skill can
WriteandEditlocal files and useWebFetchfor external network requests.\n - Sanitization: The skill does not specify validation or sanitization for the data read from the local environment.\n- [EXTERNAL_DOWNLOADS]: The skill fetches configuration guidelines from Attio's official documentation site.
Audit Metadata