persona
Pass
Audited by Gen Agent Trust Hub on Apr 29, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses local command-line tools to manage its workflow.
- It executes
bashscripts located in the plugin's root directory (${CLAUDE_PLUGIN_ROOT}/scripts/honne) to validate persona files and render final outputs. - It runs a
python3one-liner to parse JSON and perform date arithmetic to check for data staleness. - [DATA_INGESTION]: The skill reads from
.honne/persona.jsonto construct a payload for LLM synthesis. This is a standard pattern for personalizing agent behavior based on workspace state. - [FILE_OPERATIONS]: The skill writes generated persona data to the
.honne/cacheand.honne/personasdirectories within the current working directory.
Audit Metadata