lov-personal-vocabulary

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is a well-structured tool for local vocabulary management, utilizing standard Python logic for its core features.
  • [EXTERNAL_DOWNLOADS]: Interacts with the Typeless service through its official API (api.typeless.com). This connection is essential to the skill's purpose and follows best practices for credential handling.
  • [COMMAND_EXECUTION]: Synchronisation tasks are performed by local CLI scripts (vocab_cli.py) that handle structured data; no unsafe command execution patterns were identified.
  • [PROMPT_INJECTION]: The skill processes user-supplied vocabulary files. 1. Ingestion points: Local JSON vocabulary files. 2. Boundary markers: Mandatory user confirmation is required before any data is written or synchronized. 3. Capability inventory: File system access for data storage and network access for API synchronization. 4. Sanitization: Implements structured JSON parsing and deterministic phrase normalization to handle external content.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 12:56 AM
Security Audit — agent-trust-hub — lov-personal-vocabulary