Loading the registry…
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.
Claude Skills are markdown + scripts loaded into Claude Code; scanned with the same pipeline.
We found this by crawling public sources and nobody has attested to it. That is how most of the registry gets here, and it is not a mark against the artifact — it only means no authenticated act of publication is on record. An artifact can be the vendor's own and still appear here.
46 critical findings reported by agent-audit-kit. The composite score alone does not reflect this — read the per-scanner reports below.
Claude Skills install to a single target, no runtime picker.
nerlo install -- 'sueytame/claude-skills-collection (agent-browser)'
Manual alternative: copy the skill folder into ~/.claude/skills/ so Claude Code loads it on next launch.
cp -r -- 'sueytame/claude-skills-collection (agent-browser)' ~/.claude/skills/
Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.
4 of 11 scanners examined this package. The rest do not apply to it — language, ecosystem and packaging decide which analyzers can say anything, and a scanner that cannot examine an artifact reports nothing rather than passing it.
v2.0.11
Timed out
0 findings · 300.0s
v0.3.74
157 findings · 286.2s
v0.1.0
325 findings · 143.9s
v0.1.0
201 findings · 144.1s
v1.4.0
None of the entry points this scanner reads were found in this artifact. What each scanner covers
0 findings · 0.3s
vv0.3.2
No Go packages were found in this artifact. What each scanner covers
0 findings · 0.4s
v0.1.0
This scanner found nothing in this artifact that it assesses. What each scanner covers
0 findings · 1.2s
No report in this scan: govulncheck, osv-scanner, trivy, trivy_image.
1 scan on record. Every scan's full results are retained immutably for 24 months.
| Completed | Composite | Change | Scanners | Status |
|---|---|---|---|---|
| Aug 20, 2026 | Scan Halted | — | agentshield ·n/a: not applicablecisco-skill-scanner ·!: timeoutagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·n/a: not applicablenerlo-multi-source ·n/a: not applicable | rejected |
Findings in files this artifact installs stand as reported; a model re-read the rest and said which ones it believes are false positives. This is a second opinion published beside the evidence, not a correction to it: the per-scanner reports above are unchanged, every dismissed finding is still listed there at its original severity, and the score and the Flagged badge are computed from those raw severities alone. Nothing below moved them.
Out of 683 findings across every scanner that examined this package. None of the 46 findings rated critical by their scanner were dismissed.
Not reviewed is not the same as clean. Those 636 findings stand exactly as their scanners reported them, at full severity, as they would have without this review.
The model could have called any of these a false positive and did not.
22 AAK-OAUTH-007
Files: plugins/cybersecurity/skills/deploying-edr-agent-with-crowdstrike/scripts/process.py, plugins/cybersecurity/skills/implementing-delinea-secret-server-for-pam/scripts/agent.py, plugins/cybersecurity/skills/performing-blind-ssrf-exploitation/scripts/agent.py and 19 more · reported by agent-audit-kit
6 AAK-TASKS-003
Files: plugins/cybersecurity/skills/implementing-soar-playbook-with-palo-alto-xsoar/scripts/process.py, plugins/cybersecurity/skills/performing-dynamic-analysis-with-any-run/scripts/agent.py, plugins/cybersecurity/skills/detecting-mimikatz-execution-patterns/scripts/agent.py and 3 more · reported by agent-audit-kit
5 AAK-TASKS-004
Files: plugins/cybersecurity/skills/implementing-soar-playbook-with-palo-alto-xsoar/scripts/process.py, plugins/cybersecurity/skills/performing-dynamic-analysis-with-any-run/scripts/agent.py, plugins/cybersecurity/skills/performing-automated-malware-analysis-with-cape/scripts/agent.py and 2 more · reported by agent-audit-kit
4 AAK-SPLUNK-TOKLOG-001
Files: plugins/cybersecurity/skills/performing-graphql-security-assessment/scripts/agent.py, plugins/cybersecurity/skills/implementing-api-key-security-controls/scripts/agent.py, plugins/cybersecurity/skills/implementing-security-monitoring-with-datadog/scripts/agent.py and 1 more · reported by agent-audit-kit
3 AAK-OAUTH-008
Files: plugins/cybersecurity/skills/implementing-canary-tokens-for-network-intrusion/scripts/agent.py, plugins/cybersecurity/skills/implementing-scim-provisioning-with-okta/scripts/process.py, plugins/cybersecurity/skills/performing-deception-technology-deployment/scripts/agent.py · reported by agent-audit-kit
2 AAK-OAUTH-001
Files: plugins/cybersecurity/skills/auditing-entra-id-with-aadinternals/scripts/agent.py, plugins/cybersecurity/skills/securing-agentic-ai-tool-invocation/scripts/agent.py · reported by agent-audit-kit
2 AAK-OAUTH-006
Files: plugins/cybersecurity/skills/testing-oauth2-implementation-flaws/scripts/agent.py, plugins/cybersecurity/skills/exploiting-oauth-misconfiguration/scripts/agent.py · reported by agent-audit-kit
2 opt.nerlo-rules.nerlo-py-dynamic-exec
Files: /repo/plugins/cybersecurity/skills/performing-threat-emulation-with-atomic-red-team/scripts/agent.py · reported by nerlo-behavioral
1 AAK-OAUTH-005
Files: plugins/cybersecurity/skills/implementing-scim-provisioning-with-okta/scripts/process.py · reported by agent-audit-kit
514 The review call did not complete.
Rules: AAK-SKILL-003, AAK-SKILL-001, AAK-SECRET-003 and 11 more · Files: plugins/engineering-lifecycle/skills/security-and-hardening/SKILL.md, plugins/cybersecurity/skills/building-ioc-enrichment-pipeline-with-opencti/SKILL.md, plugins/cybersecurity/skills/auditing-mcp-servers-for-tool-poisoning/SKILL.md and 278 more · reported by agent-audit-kit, nerlo-behavioral, nerlo-install-instruction
121 The model called these false positives and our own check did not agree, so the dismissal was refused.
Rules: AAK-SKILL-005, opt.nerlo-rules.nerlo-install-destructive-system-command, AAK-HEALTHCARE-AI-005 and 3 more · Files: plugins/cybersecurity/skills/orchestrating-llm-attacks-with-pyrit/SKILL.md, plugins/cybersecurity/skills/red-teaming-llms-with-garak/SKILL.md, plugins/cybersecurity/skills/continuous-llm-red-teaming-with-promptfoo/SKILL.md and 75 more · reported by agent-audit-kit, nerlo-install-instruction
1 The model did not answer for these findings.
Rules: AAK-SKILL-002 · Files: plugins/cybersecurity/skills/detecting-indirect-prompt-injection/SKILL.md · reported by agent-audit-kit
Artifact enables credential access, shell execution, and PII handling.
The artifact contains code capable of credential access and shell command execution. Findings `AAK-SECRET-003` and `AAK-LLM-SQL-RCE-001` in `scripts/agent.py` indicate these capabilities. Additionally, `AAK-INDIA-PII-001` suggests handling of sensitive PII, and multiple `AAK-SKILL-001` and `AAK-SKILL-003` findings point to broad skill execution capabilities.
Concern level assessed by the review: Critical. This is the review's scale, not the registry badge.
Reviewed by gemini-2.5-flash. The model sees the findings, not your code, and cannot change a score.
Showing 25 of 25; the rest are in the per-scanner reports above.