plaud-recordings-to-google-calendar-events
Pass
Audited by Gen Agent Trust Hub on Jul 25, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill processes Plaud transcripts, which are external, untrusted data sources. This creates a surface for indirect prompt injection, where malicious instructions spoken in a recording could influence the agent's actions during event extraction or ledger logging.- Ingestion points: Plaud recordings and transcripts fetched in Steps 2 and 4.- Boundary markers: None; there are no instructions to the agent to disregard instructions within the processed data.- Capability inventory: Google Calendar event creation and Google Sheets ledger updates.- Sanitization: None; the workflow relies on standard prompt processing without explicit filtering of transcript content.- [EXTERNAL_DOWNLOADS]: The skill setup requires downloading additional components using
npx skills add AgentPMT/agent-skills. These downloads are sourced from the vendor's own repository and are necessary for the workflow's core functionality.
Audit Metadata