obsidian-git-repo-sync

Warn

Audited by Gen Agent Trust Hub on Aug 11, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute multiple shell commands, including git init, git add, and git push. Crucially, it interpolates user-provided input (<REMOTE_URL>) directly into the command git remote add origin <REMOTE_URL>. This presents a command injection risk if the user provides a malicious string containing shell metacharacters (e.g., ;, &, or backticks).
  • [DATA_EXFILTRATION]: The skill uses the command git add -A, which stages all files and changes in the current directory for commit and subsequent upload to the remote repository. In an agentic environment where the workspace may contain sensitive files like .env, .ssh keys, or cloud credentials, this behavior can lead to the accidental exfiltration of private data to an external server.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 11, 2026, 05:24 PM
Security Audit — agent-trust-hub — obsidian-git-repo-sync