clawdbot-security
Verdict safe, but 1 finding (1 medium), mainly social engineering. Most recent scan 2026-02-05.
This package has MEDIUM severity issues due to deceptive packaging - it is not actually an Agent Skill but rather documentation for an external npm tool. The content is purely instructional documentation for running 'npx clawdbot-security-audit' commands, with no agent-executable code, no proper SKILL.md structure with YAML frontmatter and agent instructions, and no scripts for the agent to run. While the security advice itself appears legitimate (hardening Clawdbot installations), the packaging as an 'agent skill' is misleading. Additionally, there is a missing referenced file (the.py) and absent optional metadata fields. If this were an actual agent skill with executable code, it would need proper structure and security review of any scripts that perform system modifications.
Scanner's overall assessment (LLM analyzer)
Second scanner: NVIDIA SkillSpector
The two scanners disagree: Cisco found nothing and SkillSpector says do not install. One of them has a blind spot here; read the skill before trusting either. How the two scanners compare across the whole corpus: Two scanners, one corpus.
What this skill does
Security audit and hardening for Clawdbot/Moltbot installations. Detects exposed gateways, fixes permissions, enables authentication, and guides firewall/Tailscale setup.
- Package
- 3 files, 13 KB
- SKILL.md
- 517 words, 12+ sections
- Code
- JavaScript (1)
- Version
- 1.0.0
SKILL.md covers: Clawdbot Security Audit · Quick Start · Scan for issues · Scan and auto-fix · Deep scan (includes network check) · What Gets Checked · 1. Gateway Binding · 2. File Permissions · 3. Authentication · 4. Node.js Version · 5. mDNS Broadcasting · 6. External Accessibility (--deep)
Findings
MEDIUM Misleading Skill Description - Not an Agent Skill Social Engineeringllm
This package is NOT an Agent Skill but rather an npm package (npx clawdbot-security-audit). The skill description claims to provide 'Security audit and hardening for Clawdbot/Moltbot installations' but the instructions only contain documentation for running an external npm tool. There is no SKILL.md with agent instructions, no Python/Bash scripts for the agent to execute, and no actual skill functionality. This is deceptive packaging that could mislead users about what they're installing.
Instructions contain 'npx clawdbot-security-audit' commands but no agent-executable code or actual skill logic. The entire content is documentation for an external tool, not agent instructions.What is in the package
| File | Kind | Size |
|---|---|---|
SKILL.md | doc | 3.6 KB |
cli.js | script | 8.6 KB |
package.json | config | 536 B |
External hosts referenced
tailscale.com x.com github.com nodejs.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
CONFIG_FILE
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/clawdbot-security
- Raw scan result: clawdbot-security-audit-scan.json
- Badge for your README:
- Request a re-scan