agent-browser
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
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
- Package
- 9 files, 40 KB
- SKILL.md
- 1521 words, 12+ sections
- Code
- Shell (3)
- Allowed tools
Bash(agent-browser:*)
SKILL.md covers: Browser Automation with agent-browser · Quick start · Core workflow · Commands · Navigation · Snapshot (page analysis) · Interactions (use @refs from snapshot) · Get information · Check state · Screenshots & PDF · Video recording · Wait
Findings
No findings. SAFE
What is in the package
| File | Kind | Size |
|---|---|---|
SKILL.md | doc | 13 KB |
references/authentication.md | doc | 4.3 KB |
references/proxy-support.md | doc | 4.2 KB |
references/session-management.md | doc | 3.8 KB |
references/snapshot-refs.md | doc | 4.0 KB |
references/video-recording.md | doc | 3.2 KB |
templates/authenticated-session.sh | script | 4.1 KB |
templates/capture-workflow.sh | script | 1.9 KB |
templates/form-automation.sh | script | 1.6 KB |
External hosts referenced
site.com corpproxy.company.com github.com httpbin.org external-vendor.com external.com internal.company.com intranet.company.com proxy.com site1.com site2.com site3.com
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
OUTPUT_DIR LOGIN_URL APP_PASSWORD APP_USERNAME CURRENT_URL FINAL_URL FORM_URL PASSWORD RECORDING_DIR TARGET_URL USERNAME URLS
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/agent-browser-tekken
- Raw scan result: agent-browser-scan.json
- Badge for your README:
- Request a re-scan