The Agent Skills Directory

[COMMAND_EXECUTION]: The script scripts/project_kb.py utilizes subprocess.check_output to execute local git commands (e.g., rev-parse, status, diff). These calls are implemented using list-based arguments rather than string-based shell invocation, which is a secure practice that prevents shell injection vulnerabilities.
[DATA_EXFILTRATION]: Analysis of the Python scripts and Markdown instructions confirms that the skill operates entirely on the local filesystem. No network operations (such as HTTP requests or socket connections) or hardcoded external domains were found, ensuring no data is exfiltrated from the user's environment.
[SAFE]: The skill's behavior is consistent with its stated purpose of maintaining a research knowledge base. No evidence of prompt injection, obfuscation, persistence mechanisms, or privilege escalation was detected across the 12 analyzed files.

obsidian-project-memory