plaud-spoken-field-notes-to-a-structured-sheet
Pass
Audited by Gen Agent Trust Hub on Jul 25, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted spoken transcripts from Plaud recordings to populate spreadsheet rows, creating a surface for indirect prompt injection.\n
- Ingestion points: Transcripts are fetched from the Plaud tool (SKILL.md, step 4).\n
- Boundary markers: The skill does not define explicit delimiters or instructions to ignore potential commands within the transcript during extraction.\n
- Capability inventory: The workflow has the capability to write data to Google Sheets via the google-sheets tool (step 7).\n
- Sanitization: No evidence of sanitization or validation of transcript content prior to processing is provided.\n- [EXTERNAL_DOWNLOADS]: The skill references and installs external dependencies from the author's GitHub repository.\n
- Evidence: npx skills add AgentPMT/agent-skills --skill what-is-agentpmt\n
- Context: These resources belong to the vendor AgentPMT and are used for workflow setup.
Audit Metadata