open-knowledge-pack-entity-vault
Pass
Audited by Gen Agent Trust Hub on Jul 31, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is authored by a trusted vendor and references legitimate repositories and official CLI tools associated with the 'open-knowledge' ecosystem.
- [DATA_EXPOSURE]: The skill manages personal information (people, companies, meetings), but all operations are restricted to the local filesystem vault or trusted MCP integrations (meeting recorders). No unauthorized data exfiltration patterns were detected.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest external data from meeting recorders (transcripts and notes). While this presents a potential surface for indirect prompt injection, the skill includes instructions to normalize content and maintain verbatim records, and the risk is considered low and inherent to the skill's purpose as a CRM manager.
Audit Metadata