show-me-your-work
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is focused on improving transparency and accountability by maintaining an append-only decision log. It provides clear instructions for data handling and privacy, explicitly warning against logging secrets.
- [SAFE]: The included logging utility (
scripts/log.py) prevents common CSV/TSV injection attacks by sanitizing inputs and prefixing cells that begin with formula-triggering characters (e.g.,=,+,-,@) with a single quote. - [SAFE]: The skill uses localized file operations without network access, and its Python implementation relies solely on the standard library, avoiding supply chain risks from third-party dependencies.
- [SAFE]: The logging mechanism is designed to be append-only, reducing the risk of accidental or malicious data loss in existing files.
Audit Metadata