goals
Pass
Audited by Gen Agent Trust Hub on Aug 20, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local Obsidian notes (e.g., OKR Dashboard, project lists, and monthly/quarterly goal notes) to synthesize progress reports and next steps. While reading external content presents a potential attack surface, the risk is minimized by the skill's explicit 'Ask, Don't Assume' principle and the mandatory requirement to show drafts and wait for user approval before writing any updates back to the vault.
Audit Metadata