ingestion-and-connectors
Pass
Audited by Gen Agent Trust Hub on Jul 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill describes administrative workflows for source management using internal tools and best practices. It correctly instructs that sensitive tokens are hashed and not retrievable, and that environment variables are not used for credentials.
- [COMMAND_EXECUTION]: The skill provides examples of using the 'pnpm' CLI for creating sources within the workspace, which is an expected developer workflow for this system.
- [PROMPT_INJECTION]: The skill documents the ingestion of data from external sources such as Slack, GitHub, and generic webhooks. This introduces a surface for indirect prompt injection where instructions could be embedded in the ingested data. The skill addresses this by referencing existing security patterns like accessFilter and assertAccess to ensure data isolation.
Audit Metadata