clawdefender
No security findings. Scanned 1 time, most recently 2026-02-05.
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 scanner and input sanitizer for AI agents. Detects prompt injection, command injection, SSRF, credential exfiltration, and path traversal attacks. Use when (1) installing new skills from ClawHub, (2) processing external input like emails, calendar events, Trello cards, or API responses, (3) validating URLs before fetching, (4) running security audits on your workspace. Protects agents from malicious content in untrusted data sources.
- Package
- 4 files, 37 KB
- SKILL.md
- 785 words, 12+ sections
- Code
- Shell (2)
SKILL.md covers: ClawDefender · Installation · Quick Start · Audit all installed skills · Sanitize external input before processing · Validate a URL before fetching · Check text for prompt injection · Commands · Full Audit (`--audit`) · Input Sanitization (`sanitize.sh`) · Basic usage - pipe any external content · Check JSON API responses
Findings
No findings. SAFE
What is in the package
| File | Kind | Size |
|---|---|---|
.DS_Store | other | 8.0 KB |
SKILL.md | doc | 6.5 KB |
scripts/clawdefender.sh | script | 19 KB |
scripts/sanitize.sh | script | 3.8 KB |
External hosts referenced
github.com webhook.site
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
WORKSPACE SKILLS_DIR REPORT_ONLY ALLOWED_DOMAINS CREDENTIAL_EXFIL SECURITY_DIR
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/clawdefender
- Raw scan result: clawdefender-openclaw-security-prompt-injection,-rogue-skills-etc-scan.json
- Badge for your README:
- Request a re-scan