Loading the registry…
Fast headless browser for QA testing and site dogfooding. Navigate pages, interact with elements, verify state, diff before/after, take annotated screenshots, test responsive layouts, forms, uploads, dialogs, and capture bug evidence. Use when asked to open or test a site, verify a deployment, dogfood a user flow, or file a bug with screenshots. (gstack)
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.
21 critical findings reported by agent-audit-kit, 3 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/agatx/serenada, 957 findings
Claude Skills install to a single target, no runtime picker.
nerlo install -- 'agatx/serenada (gstack)'
Manual alternative: copy the skill folder into ~/.claude/skills/ so Claude Code loads it on next launch.
cp -r -- 'agatx/serenada (gstack)' ~/.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
1 finding · 0.6s
v2.0.11
Incomplete run
0 findings · 33.2s
v0.3.74
115 findings · 48.3s
v0.1.0
46 findings · 17.7s
v0.1.0
39 findings · 17.7s
vv0.3.2
Incomplete run
0 findings · 0.4s
v0.1.0
0 findings · 19.5s
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 22, 2026 | Scan Halted | — | agentshield: completecisco-skill-scanner ·!: incompleteagent-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 201 findings across every scanner that examined this package. 18 of 21 findings rated critical by their scanner were 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.
53 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-MCP-015, AAK-TAINT-001, AAK-LLM-SQL-RCE-001 and 10 more · Files: .claude/skills/gstack/test/skill-e2e-setup-gbrain-bad-token.test.ts, .claude/skills/gstack/test/skill-e2e-setup-gbrain-path4-local-pglite.test.ts, .claude/skills/gstack/test/skill-e2e-setup-gbrain-remote.test.ts and 17 more · reported by agent-audit-kit
11 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: AAK-IPI-WILD-CORPUS-001, AAK-HEALTHCARE-AI-004, opt.nerlo-rules.nerlo-install-run-bundled-artifact · Files: .claude/skills/gstack/AGENTS.md, .claude/skills/gstack/docs/skills.md, .claude/skills/gstack/docs/designs/ML_PROMPT_INJECTION_KILLER.md and 6 more · reported by agent-audit-kit, nerlo-install-instruction
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, agents-comment-injection-46775 · Files: AGENTS.md, CLAUDE.md, skills/gstack/CLAUDE.md · reported by agent-audit-kit, agentshield
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.
29 opt.nerlo-rules.nerlo-js-secret-to-network-egress
Files: /repo/.claude/skills/gstack/browse/src/browse-client.ts, /repo/.claude/skills/gstack/browse/src/cli.ts, /repo/.claude/skills/gstack/browse/src/server.ts and 14 more · reported by nerlo-behavioral
19 AAK-SECRET-004
Files: server/loadtest/run-local.sh, .claude/skills/gstack/scripts/slop-diff.ts, .claude/skills/gstack/supabase/config.sh and 12 more · reported by agent-audit-kit
18 opt.nerlo-rules.nerlo-install-run-bundled-artifact
Files: /repo/.claude/skills/gstack/CHANGELOG.md, /repo/.claude/skills/gstack/scripts/garry-output-comparison.ts, /repo/.claude/skills/gstack/scripts/gen-llms-txt.ts and 5 more · reported by nerlo-install-instruction
13 opt.nerlo-rules.nerlo-install-shell-inline-command
Files: /repo/.claude/skills/gstack/ARCHITECTURE.md, /repo/.claude/skills/gstack/CHANGELOG.md, /repo/.claude/skills/gstack/bin/gstack-memory-ingest.ts and 3 more · reported by nerlo-install-instruction
10 opt.nerlo-rules.nerlo-hardcoded-external-egress
1 The model did not answer for these findings.
Rules: AAK-LEGAL-002 · Files: samples/web/package.json · reported by agent-audit-kit
Critical path traversal and credential exposure risks
The artifact contains critical path traversal vulnerabilities in `.claude/skills/gstack/design/src/session.ts` and `.claude/skills/gstack/browse/src/server.ts`, which could allow unauthorized file access. It also exposes secrets in multiple files, including `.claude/skills/gstack/browse/src/pty-session-cookie.ts` and `.claude/skills/gstack/ios-qa/daemon/src/session-tokens.ts`, which could lead to credential access. Additionally, the artifact performs dynamic code execution and network egress with secrets, indicating potential for data transmission.
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.
Files: /repo/.claude/skills/gstack/design/prototype.ts, /repo/.claude/skills/gstack/design/src/check.ts, /repo/.claude/skills/gstack/design/src/design-to-code.ts and 5 more · reported by nerlo-behavioral
7 AAK-TAINT-003
Files: .claude/skills/gstack/browse/src/server.ts · reported by agent-audit-kit
6 opt.nerlo-rules.nerlo-dynamic-exec
Files: /repo/.claude/skills/gstack/browse/src/project-slug.ts, /repo/.claude/skills/gstack/scripts/garry-output-comparison.ts, /repo/.claude/skills/gstack/scripts/host-config-export.ts and 1 more · reported by nerlo-behavioral
5 AAK-HEALTHCARE-AI-004
Files: .claude/skills/gstack/design-consultation/SKILL.md, .claude/skills/gstack/plan-design-review/SKILL.md, .claude/skills/gstack/office-hours/SKILL.md and 2 more · reported by agent-audit-kit
5 AAK-IPI-WILD-CORPUS-001
Files: .claude/skills/gstack/ARCHITECTURE.md, .claude/skills/gstack/CHANGELOG.md, .claude/skills/gstack/README.md and 2 more · reported by agent-audit-kit
5 opt.nerlo-rules.nerlo-install-pipe-to-shell
Files: /repo/.claude/skills/gstack/.gitlab-ci.yml, /repo/.claude/skills/gstack/CHANGELOG.md, /repo/.claude/skills/gstack/bin/gstack-gbrain-install and 1 more · reported by nerlo-install-instruction
3 AAK-LEGAL-002
Files: client/package.json, tools/integration-test/package.json, tools/smoke-test/web/package.json · reported by agent-audit-kit
3 AAK-SPLUNK-TOKLOG-001
Files: .claude/skills/gstack/design/prototype.ts, .claude/skills/gstack/design/src/auth.ts, .claude/skills/gstack/browse/src/cli.ts · reported by agent-audit-kit
1 AAK-MCP-014
Files: .claude/skills/gstack/browse/src/server.ts · reported by agent-audit-kit
1 AAK-MCP-AUTH-PATHTRAVERSAL-001
Files: .claude/skills/gstack/design/src/session.ts · reported by agent-audit-kit
1 AAK-MCPFRAME-001
Files: .claude/skills/gstack/ios-qa/daemon/src/index.ts · reported by agent-audit-kit
1 AAK-SKILL-003
Files: .claude/skills/gstack/cso/SKILL.md · reported by agent-audit-kit
1 AAK-TAINT-001
Files: .claude/skills/gstack/browse/src/server.ts · reported by agent-audit-kit
1 opt.nerlo-rules.nerlo-go-hardcoded-external-egress
Files: /repo/server/push_fcm.go · reported by nerlo-behavioral
Showing 25 of 78; the rest are in the per-scanner reports above.