plaud
Pass
Audited by Gen Agent Trust Hub on Aug 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized data access were detected in the skill instructions or schema.
- [EXTERNAL_DOWNLOADS]: The skill references setup dependencies from official sources including AgentPMT's GitHub repository and ClawHub. These are well-known technology services and the author's own infrastructure.
- [PROMPT_INJECTION]: The skill processes external data (transcripts and AI-generated notes) which constitutes an indirect prompt injection surface.
- Ingestion points: Data is retrieved from the Plaud service via
get_transcriptandget_noteactions inschema.md. - Boundary markers: The skill instructions do not specify explicit delimiters for the processed content.
- Capability inventory: The skill utilizes remote tool calls for recording management and does not execute local shell commands or scripts.
- Sanitization: Content is retrieved directly from the Plaud API and presented to the agent for processing.
Audit Metadata