obsidian-automation

Pass

Audited by Gen Agent Trust Hub on May 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSCREDENTIALS_UNSAFEPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill generates and executes shell commands and Python scripts for batch file operations like note creation, frontmatter updates, and archiving. It incorporates safety measures such as dry-run flags and path validation to prevent unintended side effects.\n- [EXTERNAL_DOWNLOADS]: Recommends the global installation of the obsidian-cli npm package to interface with the Obsidian Local REST API plugin.\n- [CREDENTIALS_UNSAFE]: Handles the OBSIDIAN_API_KEY. Security instructions in SKILL.md correctly advise users to use environment variables for key management and warn against hardcoding keys in shared scripts.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted data from user notes.\n
  • Ingestion points: obsidian-cli get, grep, and cat operations in SKILL.md used to read note content.\n
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are specified when reading file data.\n
  • Capability inventory: High-privilege actions including shell command execution, file movement/deletion, and Python script generation.\n
  • Sanitization: Content from files is used directly without sanitization before being processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 18, 2026, 10:59 PM
Security Audit — agent-trust-hub — obsidian-automation