workspace-search-with-citations
Pass
Audited by Gen Agent Trust Hub on Jun 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues were detected. The skill is designed to improve the groundedness of AI responses through workspace retrieval and citation enforcement.
- [INDIRECT_PROMPT_INJECTION]: Note that the
workspace_searchtool ingests data from external sources (documents, notes, etc.) into the agent's context. While this is a standard surface for indirect prompt injection, the skill does not possess any dangerous capabilities (such as shell access or file-writing tools) that could be exploited by malicious content within the workspace, and the instructions emphasize strict adherence to verifying citations against the retrieved text.
Audit Metadata