close-day
Pass
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted data by reading and parsing sections from a user's Obsidian workday note. This creates an attack surface for indirect prompt injection if the notes contain malicious instructions.
- Ingestion points: Section 1 ('Load the cockpit') ingests content from today's workday note (SKILL.md).
- Boundary markers: The skill parses content based on specific markdown headers (e.g., 'Daily Outcome', 'Next Action'), providing structural boundaries, but lacks explicit instructions to the agent to disregard instructions embedded within that content.
- Capability inventory: The skill has the ability to read local files and modify specific sections of Obsidian notes using the Obsidian CLI.
- Sanitization: No sanitization or filtering is performed on the content retrieved from the notes.
- [COMMAND_EXECUTION]: The skill utilizes the Obsidian CLI as a dependency to interact with the local filesystem, enabling it to read, write, and update note content.
Audit Metadata