excalidraw-obsidian

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by design.
  • Ingestion points: The skill reads existing Markdown files within the Obsidian vault to reconstruct diagram elements and update them.
  • Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from interpreting instructions potentially hidden within the text elements of an existing drawing.
  • Capability inventory: The agent can write files to the local file system and execute related MCP tools.
  • Sanitization: No sanitization or validation logic is specified for the data retrieved from existing files before it is processed by the agent.
  • [DATA_EXPOSURE]: The skill is configured to access and modify files at the specific path ~/notes/obsedian/Excalidraw/. While this is central to its stated purpose of managing Obsidian diagrams, the path resides within a sensitive user directory where other notes may be stored.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 12:48 PM