Openclaw Migration

Security checks across static analysis, malware telemetry, and agentic risk

Overview

This migration skill is mostly purpose-aligned, but it appears able to migrate more secrets and API keys than the visible description highlights.

Install or run this only after a dry run. Avoid --migrate-secrets unless you explicitly want provider API keys and service tokens moved, back up ~/.hermes first, and review imported skills, command allowlists, memories, SOUL.md, and workspace instructions before using the migrated Hermes setup.

Static analysis

No static analysis findings were reported for this release.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Risk analysis

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

If secret migration is enabled, API keys or service tokens may be copied into Hermes configuration in addition to the Telegram token a user may expect.

Why it was flagged

The helper declares migration support for multiple provider/API secrets. The visible SKILL.md text says --migrate-secrets currently imports TELEGRAM_BOT_TOKEN, so the credential scope appears broader than the user-facing description.

Skill content
SUPPORTED_SECRET_TARGETS={
    "TELEGRAM_BOT_TOKEN",
    "OPENROUTER_API_KEY",
    "OPENAI_API_KEY",
    "ANTHROPIC_API_KEY",
    "ELEVENLABS_API_KEY",
    "VOICE_TOOLS_OPENAI_KEY",
}
Recommendation

Do not use --migrate-secrets or a full secret-migration mode unless you have reviewed the dry-run output and are comfortable moving each listed key; maintainers should align the documentation and metadata with the exact secret allowlist.

What this means

Existing OpenClaw allowlist entries or skills could grant Hermes behavior or command access you have not recently reviewed.

Why it was flagged

The migration intentionally changes Hermes command permissions and imports skills. This is disclosed and purpose-aligned, but it changes what the agent may be able to do later.

Skill content
- merge OpenClaw command approval patterns into Hermes `command_allowlist`
- copy OpenClaw skills into `~/.hermes/skills/openclaw-imports/`
Recommendation

Run a dry run first, review all imported allowlist entries and skills, and skip or edit anything you no longer want Hermes to use.

What this means

Private memories or old instructions may persist in Hermes and influence later sessions.

Why it was flagged

The skill migrates persistent persona, memory, user profile, and workspace instruction content into Hermes. That is expected for a migration tool, but these files can affect future agent context.

Skill content
- import `SOUL.md` into the Hermes home directory as `SOUL.md`
- transform OpenClaw `MEMORY.md` and `USER.md` into Hermes memory entries
- optionally copy the OpenClaw workspace instructions file into a chosen Hermes workspace
Recommendation

Review the imported memories, SOUL.md, and workspace instructions before relying on the migrated Hermes environment.

What this means

Users have less external provenance information for code that can modify Hermes configuration and migrate sensitive local data.

Why it was flagged

The package includes a runnable migration helper but does not provide a source repository or homepage in the supplied metadata. This is a provenance gap, not proof of malicious behavior.

Skill content
Source: unknown
Homepage: none
No install spec — this is an instruction-only skill.
Code file presence: scripts/openclaw_to_hermes.py
Recommendation

Inspect the script and verify the publisher/source before running it on important Hermes or OpenClaw data.