obsidian-canvas-creator
Pass
Audited by Gen Agent Trust Hub on Jul 24, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it processes untrusted user data, such as articles or notes, to generate structured Obsidian Canvas (.canvas) files.
- Ingestion points: External text enters the agent's context during the initial analysis step of the workflow as described in
SKILL.md. - Boundary markers: There are no instructions for the agent to use delimiters or to ignore potential instructions embedded within the input text.
- Capability inventory: The agent typically has the capability to write the generated JSON to the file system or execute commands via the terminal to save the output.
- Sanitization: The instructions do not include any logic for validating or sanitizing the input text to prevent it from influencing the agent's behavior during generation.
Audit Metadata