lode-git-daily-note
Pass
Audited by Gen Agent Trust Hub on May 8, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local bash script
scripts/git-stats.shand runsgit logcommands to retrieve repository activity. These operations are restricted to the local environment and are central to the skill's stated purpose. - [DATA_EXFILTRATION]: The skill reads local git history, the Obsidian vault content, and configuration files located in the user's home directory (
~/.lode/config.yaml). There is no evidence of network operations or attempts to transmit this data externally. - [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection (Category 8) as it processes untrusted data from git logs and external JSON files.
- Ingestion points: Commit subjects, bodies, and file change statistics are extracted via
scripts/git-stats.shandSKILL.md(Steps 2 and 3). - Boundary markers: The instructions do not define specific delimiters or "ignore" instructions for the processed commit content.
- Capability inventory: The skill possesses file-write capabilities for updating the Obsidian vault and shell execution capabilities for git analysis.
- Sanitization: The
git-stats.shscript performs basic character escaping for JSON formatting, but there is no semantic filtering of the commit data before it is presented to the agent.
Audit Metadata