adhd-body-doubling

Pass

Audited by Gen Agent Trust Hub on Jul 8, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is designed to help users with task initiation and focus through structured protocols and provides no evidence of malicious intent or behavior.
  • [COMMAND_EXECUTION]: The skill provides a bash script (scripts/start-session.sh) intended to be run locally by the user. The script is transparent and performs standard tasks such as directory creation, generating session IDs using openssl or $RANDOM, and collecting user input via read. It does not execute arbitrary remote code or interact with sensitive system files.
  • [DATA_EXPOSURE]: Session data is managed locally within the user's home directory at ~/.openclaw/skills/adhd-body-doubling/history/. The skill does not contain any network operations (e.g., curl, wget) that transmit this data to external servers.
  • [DYNAMIC_EXECUTION]: The session starter script includes a json_escape function that uses sed to sanitize user input before writing it to a JSON file. This is a best-practice measure to ensure data integrity and prevent potential injection issues if the JSON is later processed by other tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 8, 2026, 08:53 PM