Agent-driven browser automation: a Chrome extension + Node bridge exposing composable browser_* tools for scanning, execution, and evidence capture.
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.
8 critical findings reported by cisco-skill-scanner, agent-audit-kit, 3 of them in the installed artifact. The composite score alone does not reflect this — read the per-scanner reports below.
npm: browser-pilot-mcp @ 0.7.0, 1 finding
Choose your runtime: the CLI writes the mcpServers config entry for that target.
nerlo install --target claude-code -- browser-pilot-mcp
Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.
8 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
0 findings · 0.4s
v2.0.11
60 findings · 10.5s
v0.3.74
20 findings · 10.2s
v0.2.0
2 findings · 10.3s
v0.2.0
0 findings · 10.3s
v0.1.0
1 finding · 13.5s
v0.71.0
0 findings · 0.4s
v2.3.8
1 finding · 6.4s
vv0.3.2
No Go packages were found in this artifact. What each scanner covers
0 findings · 0.1s
v0.71.0
No container image was published for this artifact. What each scanner covers
0 findings · 0.0s
vv1.6.0
No Go modules were found in this artifact. What each scanner covers
0 findings · 0.1s
2 scans on record. Every scan's full results are retained immutably for 24 months.
| Completed | Composite | Change | Scanners | Status |
|---|---|---|---|---|
| Oct 4, 2026 | Flagged76 | — | agentshield: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·n/a: not applicablenerlo-multi-source: completetrivy: completeosv-scanner: completetrivy_image ·n/a: not applicablegovulncheck ·n/a: not applicable | completed |
| Aug 12, 2026 | Scan Halted | — | agentshield: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·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 84 findings across every scanner that examined this package. 5 of 8 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.
26 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-TAINT-001, COMMAND_INJECTION_JS_CHILD_PROCESS, AAK-TAINT-003 and 6 more · Files: tests/daemon/daemonContractIdentity.test.ts, /repo/tests/daemon/daemonContractIdentity.test.ts, /repo/tests/runtime/ciChangeScope.test.ts and 9 more · reported by agent-audit-kit, cisco-skill-scanner
18 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: YARA_autonomy_abuse_generic, SOCIAL_ENG_VAGUE_DESCRIPTION, MANIFEST_MISSING_LICENSE and 1 more · Files: /repo/docs/SKILL.md, /repo/.github/SKILL.md, /repo/tests/fixtures/task-history/SKILL.md · reported by cisco-skill-scanner
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.
11 DATA_EXFIL_JS_NETWORK
Files: /repo/scripts/lib/browser-eval-fixtures.mjs, /repo/scripts/lib/browser-harness.mjs, /repo/scripts/run-browser-smoke.mjs and 3 more · reported by cisco-skill-scanner
4 AAK-SECRET-004
Files: src/scan/actionableRules.ts, src/kernels/abml/semanticText.ts, src/bridge/extension/static/manifest.json and 1 more · reported by agent-audit-kit
3 FILE_MAGIC_MISMATCH
Files: /repo/src/scan/domAccessibilityApiBundle.ts, /repo/src/bridge/extension/service_worker/config.ts, /repo/src/browser-runtime/pageRefRuntimeSource.ts · reported by cisco-skill-scanner
2 COMMAND_INJECTION_JS_CHILD_PROCESS
Files: /repo/src/apps/daemon/daemonControl.ts · reported by cisco-skill-scanner
2 HIDDEN_DATA_FILE
Files: /repo/.prettierrc.json, /repo/.gitleaks.toml · reported by cisco-skill-scanner
2
1 The model called these false positives and our own check did not agree, so the dismissal was refused.
Rules: SECRET_PASSWORD_VAR · Files: /repo/tests/mcp/install.test.ts · reported by cisco-skill-scanner
Artifact contains critical command injection vulnerabilities and exposes credentials.
The artifact includes critical command injection vulnerabilities in `daemonControl.ts` and `exec.ts`, allowing shell execution. Multiple high-severity findings indicate credential exposure in `intercept.ts`, `manifest.json`, `semanticText.ts`, and `actionableRules.ts`. Additionally, secrets are exposed in scripts that facilitate network egress in `capture-readme-demos.mjs` and `browser-harness.mjs`. These findings warrant immediate attention due to the potential for unauthorized system control and data exfiltration.
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, /repo/src/kernels/abml · reported by cisco-skill-scanner
2 MANIFEST_MISSING_LICENSE
Files: /repo/SKILL.md, /repo/src/kernels/abml/SKILL.md · reported by cisco-skill-scanner
2 opt.nerlo-rules.nerlo-js-secret-to-network-egress
Files: /repo/scripts/capture-readme-demos.mjs, /repo/scripts/lib/browser-harness.mjs · reported by nerlo-behavioral
2 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/src/kernels/abml/SKILL.md · reported by cisco-skill-scanner
1 AAK-ANTHROPIC-SDK-001
Files: src/apps/mcp/server.ts · reported by agent-audit-kit
1 AAK-MCP-DEPRECATED-001
Files: src/apps/mcp/server.ts · reported by agent-audit-kit
1 AAK-MCPFRAME-001
Files: src/apps/daemon/server.ts · reported by agent-audit-kit
1 AAK-OAUTH-3P-001
Files: package.json · reported by agent-audit-kit
1 AAK-SUPPLY-005
Files: package-lock.json · reported by agent-audit-kit
1 COMMAND_INJECTION_EVAL
Files: /repo/src/bridge/extension/service_worker/exec.ts · reported by cisco-skill-scanner
1 EXCESSIVE_FILE_COUNT
Files: /repo/. · reported by cisco-skill-scanner
1 GHSA-rgw5-rvv9-x895
Files: /repo/package-lock.json · reported by osv-scanner
1 nerlo-malware-obfuscated_blob
Files: npm@0.7.0:bridge/browser_pilot_bridge/manifest.json · reported by nerlo-malware