vivadicta-search-and-rewrite
Pass
Audited by Gen Agent Trust Hub on Apr 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use shell commands involving the
vivadictaCLI andjqto search, retrieve, and manipulate local transcription data. These commands are standard for the tool's documented purpose. - [PROMPT_INJECTION]: The skill displays an indirect prompt injection surface because it processes untrusted transcription data through AI presets.
- Ingestion points: Transcription content is retrieved from the user's history via
vivadicta searchandvivadicta get(SKILL.md). - Boundary markers: No delimiters or specific "ignore instructions" warnings are used when passing transcription text to the rewrite engine.
- Capability inventory: The skill has the capability to read local transcription history and execute AI-based rewrites via the
vivadictaCLI (SKILL.md). - Sanitization: No evidence of content sanitization or validation is provided in the instructions.
Audit Metadata