skills/openclaw/skills/voicenotes/Gen Agent Trust Hub

voicenotes

Pass

Audited by Gen Agent Trust Hub on Feb 24, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or security vulnerabilities were detected during the analysis. The skill acts as a bridge to the official Voicenotes API endpoints.- [PROMPT_INJECTION]: Potential surface for indirect prompt injection was evaluated. Although the skill ingests external transcript data from 'api.voicenotes.com', it is an official integration for a well-known service. Ingestion points: 'transcript' data from GET and POST requests to the Voicenotes API (SKILL.md). Boundary markers: None explicitly defined in the API examples. Capability inventory: The skill utilizes 'curl' for API communication (SKILL.md). Sanitization: No specific sanitization logic is present in the skill's documentation, as it describes the API interaction structure. The risk is considered minimal given the official nature of the integration.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 24, 2026, 06:42 PM