Loading the registry…
Run AUTHENTICATED agent-browser automation against one or more sites by reusing your existing local browser login — stream those sites' cookies straight out of the local browser store (one Touch ID tap via the `cookiesync` CLI and its resident daemon) into a fresh agent-browser session, then do the task. Use when a browser task needs you to be logged in (dashboards, gated pages, account settings, an app that calls a separate API host, "do X on <site> as me", "use my session/cookies") and the user is already signed in via their desktop browser. macOS; authorized local use on the user's own machine.
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.
5 critical findings reported by cisco-skill-scanner, agent-audit-kit, 4 of them in the installed artifact. The composite score alone does not reflect this — read the per-scanner reports below.
This artifact ships from 2 sources and their verdicts differ. The worst is github (Flagged). Installing from a cleaner source does not mean the others are safe — check the source you actually install from.
github: https://github.com/yasyf/cc-skills, 235 findings
Claude Skills install to a single target, no runtime picker.
nerlo install -- 'yasyf/cc-skills (agent-browser-with-cookies)'
Manual alternative: copy the skill folder into ~/.claude/skills/ so Claude Code loads it on next launch.
cp -r -- 'yasyf/cc-skills (agent-browser-with-cookies)' ~/.claude/skills/
Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.
7 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.
v1.4.0
Incomplete run
0 findings · 0.6s
v2.0.11
140 findings · 21.5s
v0.3.74
38 findings · 13.7s
v0.1.0
0 findings · 5.7s
v0.1.0
7 findings · 5.7s
vv0.3.2
Incomplete run
0 findings · 0.4s
v0.1.0
0 findings · 11.7s
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 21, 2026 | Scan Halted | — | agentshield ·!: incompletecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·!: incompletenerlo-multi-source: complete | 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 185 findings across every scanner that examined this package. 1 of 5 findings rated critical by their scanner was among the dismissals.
Not reviewed is not the same as clean. Those 1 finding stand exactly as their scanners reported them, at full severity, as they would have without this review.
Two keys had to turn. The model had to name a reason from a fixed list of six, and a deterministic check of ours — over which files this artifact actually installs — had to independently agree. Anything it could not corroborate is in “not reviewed” above, at full severity.
7 Agent instruction file — The match is in a file that instructs an AI coding agent — a CLAUDE.md or similar. It is documentation of intent, and our own check confirmed it is not part of what gets installed.
Rules: AAK-AGENT-002, AAK-AGENT-003, AAK-AGENT-005 and 2 more · Files: CLAUDE.md, AGENTS.md, /repo/repo/AGENTS.md · reported by agent-audit-kit, cisco-skill-scanner
7 CI or editor configuration — The match is in build, CI or editor configuration, confirmed by our own check to be outside the installed artifact.
Rules: COMMAND_INJECTION_OS_SYSTEM, AAK-GHA-IMMUTABLE-001 · Files: /repo/.github/scripts/plugin_autobump.py, .github/workflows/plugin-autobump.yml, .github/workflows/guides-lint.yml and 3 more · reported by cisco-skill-scanner, agent-audit-kit
2 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: AAK-HEALTHCARE-AI-004, MANIFEST_MISSING_LICENSE · Files: plugins/design-doc/skills/design-doc/templates/example/NOTES.md, /repo/plugins/design-doc/skills/design-doc/templates/example/SKILL.md · reported by agent-audit-kit, cisco-skill-scanner
1 Test or fixture file — The match is in a test or fixture. Our own check confirmed the file is not part of what gets installed.
Rules: AAK-SECRET-004 · Files: tools/gd-build/tests/test_search_rank.py · reported by agent-audit-kit
These findings are in files this artifact installs and are not placeholder values. No false-positive basis can be corroborated for such a finding, so this review never dismisses one; they were not sent to the model and stand at their scanner's severity.
50 MANIFEST_MISSING_LICENSE
Files: /repo/plugins/codex/skills/codex/SKILL.md, /repo/plugins/agent-browser-with-cookies/skills/agent-browser-with-cookies/SKILL.md, /repo/plugins/show/skills/show/SKILL.md and 47 more · reported by cisco-skill-scanner
32 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/.claude/fragments/AGENTS.md/SKILL.md, /repo/plugins/codex/SKILL.md and 29 more · reported by cisco-skill-scanner
22 FILE_MAGIC_MISMATCH
Files: /repo/plugins/repo-bootstrap/skills/repo-bootstrap/templates/base/README.md, /repo/plugins/repo-bootstrap/skills/repo-bootstrap/templates/bun/README.md, /repo/plugins/repo-bootstrap/skills/repo-bootstrap/templates/go/README.md and 4 more · reported by cisco-skill-scanner
13 AAK-MARKETPLACE-001
Files: .claude-plugin/marketplace.json · reported by agent-audit-kit
8 MANIFEST_INVALID_NAME
Files: /repo/.claude/fragments/AGENTS.md/SKILL.md, /repo/plugins/repo-bootstrap/skills/repo-bootstrap/templates/python/claude/fragments/AGENTS.md/SKILL.md, /repo/plugins/repo-bootstrap/skills/repo-bootstrap/templates/bun/claude/fragments/AGENTS.md/SKILL.md and 5 more
1 The model did not answer for these findings.
Rules: SOCIAL_ENG_VAGUE_DESCRIPTION · Files: /repo/plugins/design-doc/skills/design-doc/templates/example/SKILL.md · reported by cisco-skill-scanner
Artifact contains critical injection vulnerabilities and potential for shell execution.
The artifact includes code susceptible to coercive injection in multiple files, including shell scripts, which could lead to arbitrary command execution. It also contains high-severity findings related to undeclared network activity, potential infinite loops, and the presence of sensitive data. These issues indicate capabilities for network egress, shell execution, and credential access within the installed code.
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.
4 AAK-HEALTHCARE-AI-004
Files: plugins/codex/skills/codex/SKILL.md, plugins/repo-bootstrap/skills/repo-bootstrap/reference/hooks.md, plugins/design-doc/skills/design-doc/reference/method.md and 1 more · reported by agent-audit-kit
4 HIDDEN_DATA_FILE
Files: /repo/.pre-commit-config.yaml, /repo/plugins/codex/.golangci.yml, /repo/.superset/config.json · reported by cisco-skill-scanner
4 opt.nerlo-rules.nerlo-install-run-bundled-artifact
Files: /repo/plugins/repo-bootstrap/skills/apple-certs/scripts/check-p12-chain.sh, /repo/plugins/repo-bootstrap/skills/repo-bootstrap/reference/ci-and-release.md, /repo/plugins/repo-bootstrap/skills/repo-bootstrap/reference/go-ci-and-release.md and 1 more · reported by nerlo-install-instruction
3 ALLOWED_TOOLS_BASH_VIOLATION
Files: /repo/plugins/repo-bootstrap/skills/apple-certs/repo/plugins/repo-bootstrap/skills/apple-certs/SKILL.md, /repo/plugins/design-doc/skills/design-doc/repo/plugins/design-doc/skills/design-doc/SKILL.md, /repo/plugins/gh-profile/skills/gh-profile/repo/plugins/gh-profile/skills/gh-profile/SKILL.md · reported by cisco-skill-scanner
3 opt.nerlo-rules.nerlo-install-shell-inline-command
Files: /repo/plugins/repo-bootstrap/skills/repo-bootstrap/reference/go-ci-and-release.md, /repo/plugins/writing-docs/skills/writing-docs/references/honesty-gates.md, /repo/plugins/writing-docs/skills/writing-docs/references/worked-example.md · reported by nerlo-install-instruction
3 RESOURCE_ABUSE_INFINITE_LOOP
Files: /repo/plugins/codex/capt-hook/hooks/dispatch.py, /repo/tools/await-release.py · reported by cisco-skill-scanner
3 YARA_coercive_injection_generic
Files: /repo/plugins/repo-bootstrap/skills/apple-certs/scripts/assemble-p12.sh, /repo/plugins/llm-prompts/skills/llm-prompts/reference/SKILL.md · reported by cisco-skill-scanner
2 DATA_EXFIL_NETWORK_REQUESTS
Files: /repo/plugins/repo-bootstrap/skills/repo-bootstrap/scripts/bootstrap/pypi.py · reported by cisco-skill-scanner
2 EXCESSIVE_FILE_COUNT
Files: /repo/., /repo/plugins/repo-bootstrap/skills/repo-bootstrap/. · reported by cisco-skill-scanner
2 MANIFEST_DESCRIPTION_TOO_LONG
Files: /repo/plugins/writing-docs/skills/writing-docs/SKILL.md, /repo/plugins/codex/skills/codex/SKILL.md · reported by cisco-skill-scanner
2 TOOL_ABUSE_UNDECLARED_NETWORK
Files: /repo/plugins/gen-image/skills/gen-image/repo/plugins/gen-image/skills/gen-image/SKILL.md, /repo/plugins/repo-bootstrap/skills/repo-bootstrap/repo/plugins/repo-bootstrap/skills/repo-bootstrap/SKILL.md · reported by cisco-skill-scanner
1 AAK-MCP-006
Files: plugin/guides/json/mcp-swift.json · reported by agent-audit-kit
1 AAK-MCP-ATTEST-001
Files: plugin/guides/json/mcp-swift.json · reported by agent-audit-kit
1 AAK-SECRET-004
Files: plugins/gh-profile/skills/gh-profile/templates/github/summaries.config.json · reported by agent-audit-kit
1 AAK-SKILL-001
Files: plugins/repo-bootstrap/skills/repo-bootstrap/templates/swift/claude/skills/xcodebuildmcp-cli/SKILL.md · reported by agent-audit-kit
1 AAK-TRUST-004
Files: .claude/settings.json · reported by agent-audit-kit
1 AAK-TRUST-006
Files: .claude/settings.json · reported by agent-audit-kit
1 AAK-TRUST-007
Files: .claude/settings.json · reported by agent-audit-kit
1 ALLOWED_TOOLS_GREP_VIOLATION
Files: /repo/plugins/repo-bootstrap/skills/apple-certs/repo/plugins/repo-bootstrap/skills/apple-certs/SKILL.md · reported by cisco-skill-scanner
1 LOW_ANALYZABILITY
Files: /repo/plugins/repo-bootstrap/skills/repo-bootstrap/templates/bun · reported by cisco-skill-scanner
1 SOCIAL_ENG_MISLEADING_DESC
Files: /repo/plugins/repo-bootstrap/skills/repo-bootstrap/SKILL.md · reported by cisco-skill-scanner