Loading the registry…
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.
59 critical findings reported by cisco-skill-scanner, agent-audit-kit, 39 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/microsandbox/microsandbox, 274 findings
Choose your runtime: the CLI writes the mcpServers config entry for that target.
nerlo install --target claude-code -- nerlo-ingest-_3y9uy3a
Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.
6 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
188 findings · 26.6s
v0.3.74
56 findings · 39.3s
v0.2.0
0 findings · 12.4s
v0.2.0
30 findings · 12.4s
vv0.3.2
Incomplete run
0 findings · 0.5s
v0.1.0
2 findings · 18.8s
v1.4.0
None of the entry points this scanner reads were found in this artifact. What each scanner covers
0 findings · 0.2s
No report in this scan: govulncheck, osv-scanner, trivy, trivy_image.
8 scans on record. Every scan's full results are retained immutably for 24 months.
| Completed | Composite | Change | Scanners | Status |
|---|---|---|---|---|
| Sep 11, 2026 | Scan Halted | — | agentshield ·n/a: not applicablecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·!: incompletenerlo-multi-source: complete | rejected |
| Aug 2, 2026 | Scan Halted | — | agentshield ·n/a: not applicablecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completenerlo-multi-source: complete | rejected |
| Jul 30, 2026 | Scan Halted | — | cisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completenerlo-multi-source: complete | rejected |
| Jul 21, 2026 | Scan Halted | — | agentshield ·n/a: not applicablecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: complete | rejected |
| Jul 20, 2026 | Scan Halted | — | agentshield ·n/a: not applicablecisco-skill-scanner: completeagent-audit-kit: complete | rejected |
| Jul 20, 2026 | Scan Halted | Clean → Flagged | agentshield ·n/a: not applicablecisco-skill-scanner: completeagent-audit-kit: complete | rejected |
| Jul 20, 2026 | Clean100 | — | agentshield ·n/a: not applicablecisco-skill-scanner ·n/a: not applicableagent-audit-kit: completetrivy: completeosv-scanner ·n/a: not applicable | completed |
| Jul 20, 2026 | Clean100 | — | agentshield ·n/a: not applicablecisco-skill-scanner ·n/a: not applicableagent-audit-kit: completetrivy: completeosv-scanner ·n/a: not applicable | completed |
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 276 findings across every scanner that examined this package. 20 of 59 findings rated critical by their scanner were among the dismissals.
Not reviewed is not the same as clean. Those 4 findings 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.
98 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: opt.nerlo-rules.nerlo-install-pipe-to-shell, AAK-SPLUNK-TOKLOG-001, AAK-LEGAL-002 and 13 more · Files: /repo/docs/cli/overview.mdx, /repo/docs/examples/data/juicefs-s3.mdx, /repo/docs/getting-started/introduction.mdx and 56 more · reported by nerlo-install-instruction, agent-audit-kit, cisco-skill-scanner
28 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: YARA_command_injection_generic, COMMAND_INJECTION_EVAL, AAK-SECRET-004 and 1 more · Files: /repo/sdk/go/integration/fs_test.go, /repo/examples/python/fs-read-stream/main.py, /repo/examples/python/metrics-stream/main.py and 10 more · reported by cisco-skill-scanner, agent-audit-kit
4 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-003, TOOL_ABUSE_UNDECLARED_NETWORK · Files: AGENTS.md, /repo/repo/AGENTS.md, /repo/examples/repo/examples/README.md and 1 more · reported by agent-audit-kit, cisco-skill-scanner
1 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: MANIFEST_INVALID_NAME · Files: /repo/.github/ISSUE_TEMPLATE/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.
20 AAK-TAINT-002
Files: sdk/rust/lib/sandbox/patch.rs, crates/image/lib/ext4/formatter.rs, crates/agentd/lib/tls.rs and 1 more · reported by agent-audit-kit
18 UNANALYZABLE_BINARY
Files: /repo/sdk/go/internal/bundle/bundles/libmicrosandbox_go_ffi-darwin-arm64.dylib, /repo/sdk/rust/fuzz/seeds/unpack_archive/sparse.tar!/sha256-0000000000000000/upper.ext4, /repo/sdk/go/internal/bundle/bundles/libmicrosandbox_go_ffi-linux-arm64.so and 6 more · reported by cisco-skill-scanner
16 MANIFEST_MISSING_LICENSE
Files: /repo/SKILL.md, /repo/packages/microsandbox-types/SKILL.md, /repo/packages/agent-client/SKILL.md and 13 more · reported by cisco-skill-scanner
16 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/packages/microsandbox-types/SKILL.md, /repo/packages/agent-client/SKILL.md and 13 more · reported by cisco-skill-scanner
12 COMMAND_INJECTION_EVAL
Files: /repo/sdk/node-ts/native/index.d.ts, /repo/sdk/node-ts/src/internal/napi.ts, /repo/sdk/node-ts/src/sandbox.ts and 1 more
4 The model called these false positives and our own check did not agree, so the dismissal was refused.
Rules: BINARY_FILE_DETECTED · Files: /repo/sdk/rust/fuzz/seeds/unpack_archive/sparse.tar!/sha256-0000000000000000/upper.ext4, /repo/sdk/rust/fuzz/seeds/unpack_archive/dense.tar!/sha256-0000000000000000/upper.ext4 · reported by cisco-skill-scanner
Artifact allows shell execution and system modification.
The artifact contains code that can execute arbitrary commands via shell processes, specifically in `sdk/node-ts/bin/microsandbox.cjs`. It also includes code capable of system modification, as seen in `scripts/ci/provision-runners.sh`. Additionally, there are multiple instances of critical taint findings in core Rust components and the Rust SDK, indicating potential for untrusted input to influence sensitive operations. The artifact also contains embedded secrets.
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.
10 BINARY_FILE_DETECTED
Files: /repo/sdk/go/internal/bundle/bundles/libmicrosandbox_go_ffi-windows-arm64.dll, /repo/sdk/go/internal/bundle/bundles/libmicrosandbox_go_ffi-windows-amd64.dll, /repo/sdk/go/internal/bundle/bundles/libmicrosandbox_go_ffi-linux-arm64.so and 2 more · reported by cisco-skill-scanner
8 DATA_EXFIL_NETWORK_REQUESTS
Files: /repo/scripts/ci/publish-crates.py, /repo/scripts/smoke/cli/previous_release_upgrade.py, /repo/scripts/sync-docs-openapi.py · reported by cisco-skill-scanner
7 AAK-SECRET-004
Files: sdk/rust/lib/backend/profile.rs, sdk/rust/lib/backend/cloud/mod.rs, crates/network/lib/dns/nameserver/scdynamicstore.rs and 3 more · reported by agent-audit-kit
5 HIDDEN_DATA_FILE
Files: /repo/.cargo/config.toml, /repo/.taplo.toml, /repo/.pre-commit-config.yaml and 2 more · reported by cisco-skill-scanner
4 ARCHIVE_FILE_DETECTED
Files: /repo/sdk/rust/fuzz/seeds/unpack_archive/dense.tar, /repo/sdk/rust/fuzz/seeds/unpack_archive/sparse.tar · reported by cisco-skill-scanner
4 COMMAND_INJECTION_JS_CHILD_PROCESS
Files: /repo/sdk/node-ts/native/index.cjs, /repo/sdk/node-ts/bin/microsandbox.cjs · reported by cisco-skill-scanner
4 EXCESSIVE_FILE_COUNT
Files: /repo/sdk/node-ts/., /repo/., /repo/sdk/rust/. and 1 more · reported by cisco-skill-scanner
4 LOW_ANALYZABILITY
Files: /repo/packages/microsandbox-types/typescript, /repo/sdk/node-ts, /repo/packages/agent-client and 1 more · reported by cisco-skill-scanner
4 YARA_system_manipulation_generic
Files: /repo/scripts/ci/provision-runners.sh · reported by cisco-skill-scanner
3 opt.nerlo-rules.nerlo-install-pipe-to-shell
Files: /repo/DEVELOPMENT.md, /repo/README.md, /repo/scripts/install.sh · reported by nerlo-install-instruction
2 nerlo-malware-obfuscated_blob
Files: github_release:agentd-x86_64, github_release:agentd-aarch64 · reported by nerlo-malware
2 TOOL_ABUSE_SYSTEM_MODIFICATION
Files: /repo/scripts/ci/provision-runners.sh · reported by cisco-skill-scanner
1 AAK-SUPPLY-005
Files: Cargo.lock · reported by agent-audit-kit
1 COMPOUND_FETCH_EXECUTE
Files: /repo/scripts/smoke/cli/pre05-running-sandbox-compat.sh · reported by cisco-skill-scanner
Showing 25 of 53; the rest are in the per-scanner reports above.