zettel-brainstormer
Pass
Audited by Gen Agent Trust Hub on Apr 10, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes several local Python scripts (setup.py, find_links.py, compile_preprocess.py) to manage the note-processing pipeline. These scripts use standard Python libraries to perform file I/O operations and regex-based text parsing within the configured local directories.
- [DATA_EXFILTRATION]: No network-based exfiltration patterns or unauthorized remote connections were identified. All data processing is confined to the local filesystem and the agent's execution environment.
- [PROMPT_INJECTION]: The skill instructions and agent prompts in the agents/ directory follow standard operational logic. No attempts to override safety filters, extract system prompts, or bypass agent constraints were found.
- [EXTERNAL_DOWNLOADS]: The skill references an external tool, zettel-link, for semantic retrieval. The usage instructions involve local execution (uv run) and do not involve downloading or executing code from untrusted remote sources.
Audit Metadata