moltbot-ha
Verdict safe, but 2 findings (2 medium), mainly data exfiltration, unauthorized tool use. Most recent scan 2026-02-06.
The moltbot-ha skill is a legitimate Home Assistant control interface with moderate security concerns. The skill correctly implements safety confirmations for critical operations (locks, alarms, garage doors), but has weaknesses in credential handling guidance and the --force bypass mechanism. The primary risks are: (1) potential credential exposure through insecure token storage practices, (2) safety bypass via --force flag that relies on agent-level confirmation rather than tool-level enforcement. The skill does not contain malicious code, data exfiltration, or prompt injection attempts. It's a functional smart home control tool that would benefit from enhanced security documentation and stronger confirmation mechanisms for critical operations. The missing metadata fields and referenced file are minor documentation issues.
Scanner's overall assessment (LLM analyzer)
Second scanner: NVIDIA SkillSpector
Independent static run, no language model, over the same files as the Cisco scan above. How the two scanners compare across the whole corpus: Two scanners, one corpus.
What this skill does
Control Home Assistant smart home devices, lights, scenes, and automations via moltbot-ha CLI with configurable safety confirmations.
- Package
- 4 files, 20 KB
- SKILL.md
- 903 words, 12+ sections
- Code
- None. Instructions only.
- Requires
- bins:
moltbot-ha; env:HA_TOKEN
SKILL.md covers: Home Assistant Control · Setup · 1. Install moltbot-ha · 2. Initialize Configuration · 3. Set Environment Variable · 4. Test Connection · Discovery Commands · List All Entities · List by Domain · Get Entity State · Action Commands · Turn On/Off
Findings
MEDIUM Hardcoded Credential Exposure Risk in Documentation Data Exfiltrationllm
The skill instructions demonstrate setting the HA_TOKEN environment variable with a placeholder 'your_token_here' and provide detailed steps for creating long-lived access tokens. While educational, this pattern could lead users to hardcode sensitive tokens in shell history or configuration files. The skill requires HA_TOKEN as a primary environment variable but lacks guidance on secure token storage practices.
SKILL.md
export HA_TOKEN="your_token_here" - Instructions show direct environment variable setting without warnings about shell history, secure storage, or token rotation best practices.MEDIUM Critical Action Bypass via --force Flag Unauthorized Tool Usellm
The skill implements a 3-level safety system for critical operations (locks, alarms, garage doors), but the confirmation mechanism can be bypassed using a --force flag. While the workflow requires agent-to-user confirmation before using --force, this creates a potential tool exploitation vector if the agent's decision-making is compromised or if prompt injection causes the agent to skip user confirmation.
SKILL.md
Example: moltbot-ha on cover.garage --force - The --force flag allows bypassing safety confirmations for critical operations like garage doors and door locks.What is in the package
| File | Kind | Size |
|---|---|---|
CHANGELOG.md | doc | 2.0 KB |
README.md | doc | 9.5 KB |
SKILL.md | doc | 7.2 KB |
config.example.toml | config | 1.6 KB |
External hosts referenced
github.com homeassistant.ts.net img.shields.io xxxxx.ui.nabu.casa clawdhub.com developers.home-assistant.io docs.molt.bot keepachangelog.com molt.bot rich.readthedocs.io semver.org typer.tiangolo.com www.home-assistant.io www.python.org
Hostnames that appear in the skill's files. Referencing a host is not a finding; compare against the findings above and the skill's stated purpose.
Environment variables referenced
HA_TOKEN HA_URL HA_CTL_CONFIG
Package contents recorded 2026-10-22. The scan above ran against the version current at scan time; the two can differ if the skill has since been updated.
What we checked
- Static analyzer. Pattern rules over SKILL.md and bundled files: known-bad commands, exfiltration URLs, secrets, obfuscation.
- Behavioral analyzer. Checks what the skill asks the agent to do against what its description claims it does.
- Llm analyzer. A language model reads the skill and reports intent-level issues the rules cannot express.
- Trigger analyzer. Looks for instructions that fire on conditions the user did not ask for.
- Meta analyzer. A second model pass that validates, deduplicates and re-scores the other analyzers' findings.
What we did not check
- Runtime behaviour. The skill was not executed; findings come from reading its files.
- Anything fetched at install or run time, including remote scripts, package dependencies, and URLs the skill tells the agent to open.
- Content the analyzers cannot read: images, binaries, and some non-English text.
- Known scanner bypass classes. See the methodology and limitations page.
Sources
- Repository: https://clawhub.ai/skills/moltbot-ha
- Raw scan result: moltbot-home-assistant-scan.json
- Badge for your README:
- Request a re-scan