migrate-openclaw
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill imports memory, skills, and agent configurations from an external source directory (~/.openclaw/).
- Ingestion points: Data is read from the
~/.openclaw/directory to populate the agent's memory and skill folders. - Boundary markers: The instructions do not define specific delimiters or warnings to prevent the LLM from obeying instructions potentially embedded in the imported data.
- Capability inventory: The skill utilizes
Write,Edit, andBashtools to modify the agent's memory files, skill files, and core configuration (CLAUDE.md). - Sanitization: There is no mention of sanitizing or validating the content being imported from the source directory before it is committed to the agent's environment.
- [COMMAND_EXECUTION]: The skill relies on executing a local Node.js script (
scripts/migrate-openclaw.cjs) via the command line. - The agent is instructed to run this script using
nodewith various arguments like--dry-runand--mergeto perform the migration logic. - The skill documentation includes a fallback step to use
chmod +xto ensure the script is executable, which is a standard procedure for local tooling.
Audit Metadata