obsidian-canvas
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use shell commands including 'mv' and 'wc' to manage file updates and verify the state of generated Obsidian Canvas files. This is intended to prevent race conditions during file synchronization.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data like reading summaries and notes to build visualizations, which introduces a surface for indirect instructions.
- Ingestion points: The skill reads content from Obsidian notes and project data.
- Boundary markers: No delimiters or ignore-instructions are specified for the processed content.
- Capability inventory: The agent can read, write, and edit files, and execute shell commands (mv, wc).
- Sanitization: No sanitization of the input content is described before inclusion in the canvas.
Audit Metadata