daily
Pass
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill ingests data from external Obsidian notes and project files to generate proposals for the user, creating a surface for indirect prompt injection where malicious content in those files could influence agent behavior. \n
- Ingestion points: Step 3 performs reads on the current daily note, weekly notes, prior workday notes, and flat project lists (SKILL.md). \n
- Boundary markers: The instructions do not specify boundary markers or include explicit directions for the agent to ignore instructions embedded within the processed file content. \n
- Capability inventory: The skill possesses the capability to read, create, and patch local files via the
obsidianCLI tool (SKILL.md). \n - Sanitization: The risk is significantly mitigated by a mandatory human commitment gate in Step 4, which requires the user to explicitly confirm or write the daily outcome and next action before the agent updates any named sections.
Audit Metadata