manage-amp-context
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides administrative tools to list projects and update organization or project-level AI context. It includes documentation regarding required permission levels (admin/manager) for these operations.
- [INDIRECT_PROMPT_INJECTION]: The
set_org_contextandset_project_contextfunctions allow for the ingestion of up to 10,000 characters of external data into the Amplitude context store. While this represents a data ingestion surface that could store instructions intended for other agents, it is a core feature of the skill and the instructions mandate user confirmation of the replacement text before execution.
Audit Metadata