periodic-rollup

Pass

Audited by Gen Agent Trust Hub on Feb 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION] (LOW): The skill is vulnerable to indirect prompt injection (Category 8) as it ingests content from vault notes during history and periodic rollups.
  • Ingestion points: Note content is retrieved from the '01-Days' and '03-Records' folders via 'rg' and 'obsidian-cli'.
  • Boundary markers: Absent; the skill lacks delimiters or 'ignore embedded instructions' warnings for processed data.
  • Capability inventory: Includes file creation ('obsidian-cli create') and file reading ('obsidian-cli search-content').
  • Sanitization: Absent; there is no logic to escape or validate content before it is processed by the AI or used in commands.
  • [COMMAND_EXECUTION] (LOW): The skill utilizes local shell commands ('rg', 'obsidian-cli') for its core functionality. While appropriate for the use case, this constitutes a local command execution surface.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 19, 2026, 10:33 PM