secondbrain-task
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [Data Exposure & Exfiltration] (SAFE): The skill accesses local files within the .claude/data/tasks/ and docs/tasks/ directories to manage task records. No sensitive system files are accessed, and no network operations are performed to exfiltrate data.
- [Indirect Prompt Injection] (SAFE): The skill possesses an ingestion surface for untrusted user data (Step 1: Title, Description). While boundary markers and sanitization are absent, the data is strictly written to static YAML and Markdown files and is not re-interpreted as executable code or agent instructions, minimizing risk.
- [Unverifiable Dependencies & Remote Code Execution] (SAFE): No external dependencies are requested or installed, and there are no instances of remote script execution or dynamic code evaluation.
Audit Metadata