skills/agentpmt/agent-skills/one-plaud-recording-several-differently-formatted-summaries/Gen Agent Trust Hub
one-plaud-recording-several-differently-formatted-summaries
Pass
Audited by Gen Agent Trust Hub on Jul 25, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructions provide commands to install dependencies using "npx skills add AgentPMT/agent-skills". These downloads originate from the vendor's official repository.
- [PROMPT_INJECTION]: The skill processes untrusted external data (Plaud transcripts and Google Sheet cell content) to generate summaries. This creates a surface for indirect prompt injection where instructions hidden in a transcript or sheet could influence the agent's output.
- Ingestion points: Transcripts fetched from Plaud API and format definitions read from Google Sheets (SKILL.md).
- Boundary markers: None identified in the prompt instructions to isolate external content from system instructions.
- Capability inventory: Reading audio transcripts, reading/writing to Google Sheets, and creating Google Docs via MCP/REST tools.
- Sanitization: No explicit sanitization or validation of the input text is described in the workflow instructions.
Audit Metadata