obsidian-backlinks

Pass

Audited by Gen Agent Trust Hub on Apr 16, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the obsidian CLI to perform shell-based operations, such as reading file content and retrieving vault path information (obsidian read, obsidian vault info). These operations are scoped to the local environment and intended for note management.
  • [DATA_EXPOSURE_AND_EXFILTRATION]: The skill accesses local files within the user's Obsidian vault and a configuration file named .concepts.yaml located in the workspace. There are no indicators of data being transmitted to external servers or unauthorized access to sensitive system directories.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from Obsidian notes which could theoretically contain malicious instructions.
  • Ingestion points: Content is read from user-controlled markdown files via obsidian read (SKILL.md).
  • Boundary markers: The skill does not define specific delimiters or warnings to ignore instructions embedded within the notes.
  • Capability inventory: The agent can execute shell commands via the obsidian CLI and write files using the write tool (SKILL.md).
  • Sanitization: No explicit sanitization or validation of the ingested note content is mentioned before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 16, 2026, 05:22 AM