second-brain-review
Pass
Audited by Gen Agent Trust Hub on Jul 8, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Python script (
pick-review.py) to determine which content to surface. This script uses standard file system operations to read and parse local Markdown files. - [DATA_EXPOSURE]: The skill accesses local files in a designated 'vault' directory (defaulting to
~/Documents/sanket-wiki). This is consistent with its stated purpose of managing a personal knowledge base. No sensitive system files or credentials outside this directory are accessed. - [REMOTE_CODE_EXECUTION]: There are no network operations, external downloads, or execution of remote code. All operations are local.
- [PROMPT_INJECTION]: The instructions do not contain patterns attempting to override agent behavior or safety guidelines. The guidelines provided for the 'review' process are conversational and content-focused.
Audit Metadata