hi-light Ear Skill

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

Overview

The skill mostly matches its HiLight setup purpose, but it may expose your API key in command output and enables a broadly open HiLight channel by default.

Only run this if you trust the HiLight plugin and are comfortable giving it your API key. Prefer a dry run first, ask the agent not to print full config output, and consider restricting dmPolicy/allowFrom rather than using the open wildcard defaults.

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.

#ASI02: Tool Misuse and Exploitation

Low

What this means

Running the skill can change your OpenClaw setup and restart its gateway service.

Why it was flagged

The script installs/enables an OpenClaw plugin and restarts the gateway. This is disclosed and purpose-aligned, but it materially changes the user's OpenClaw environment.

Skill content

run_cmd openclaw plugins install "$PLUGIN_SPEC"
...
run_cmd openclaw plugins enable "$PLUGIN_ID"
...
run_cmd openclaw gateway restart

Recommendation

Use --dry-run first if you want to preview changes, and use --no-restart if you do not want the gateway restarted automatically.

#ASI04: Agentic Supply Chain Vulnerabilities

Low

What this means

You are trusting the external @art_style666/hi-light plugin code that OpenClaw installs.

Why it was flagged

The skill installs an external plugin package as part of its normal workflow. This is central to the skill, but the provided registry metadata lists no source homepage, so provenance is not independently established in the artifacts.

Skill content

PLUGIN_SPEC="${PLUGIN_SPEC:-@art_style666/hi-light}"
...
run_cmd openclaw plugins install "$PLUGIN_SPEC"

Recommendation

Verify that @art_style666/hi-light is the intended trusted HiLight plugin before running the setup.

#ASI03: Identity and Privilege Abuse

Medium

What this means

Your HiLight API key could appear in local command output, logs, or an agent transcript.

Why it was flagged

After writing the API key into authToken, the script retrieves the full hi-light channel JSON. The artifacts do not show redaction, so the stored token may be printed in terminal/tool output despite the SKILL.md instruction not to repeat the token.

Skill content

run_cmd openclaw config set 'channels["hi-light"].authToken' "$API_KEY"
...
echo "[INFO] Current hi-light channel summary"
run_cmd openclaw config get 'channels["hi-light"]' --json

Recommendation

Do not print the full channel config after storing the key; redact authToken or query only non-secret fields. Treat the API key as a declared credential.

#ASI07: Insecure Inter-Agent Communication

Medium

What this means

If these settings control who can message the OpenClaw channel, the default may accept a broad set of HiLight senders rather than a restricted list.

Why it was flagged

The default channel policy is open and allows from wildcard '*'. The workflow does not clearly explain the inbound-message boundary or prompt users to narrow allowed senders.

Skill content

DEFAULT_DM_POLICY="open"
DEFAULT_ALLOW_FROM='["*"]'
...
run_cmd openclaw config set 'channels["hi-light"].dmPolicy' "$DM_POLICY"
run_cmd openclaw config set 'channels["hi-light"].allowFrom' "$ALLOW_FROM"

Recommendation

Before enabling the channel, confirm what dmPolicy and allowFrom mean for HiLight and consider setting a restricted allowFrom list instead of the wildcard default.