Use when taking over or resuming a research or engineering project, maintaining continuity across sessions, comparing experiments, reviewing evidence, managing hypotheses, recovering context, or supervising one task-oriented action.
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.
92 critical findings reported by cisco-skill-scanner, 72 of them in the installed artifact. 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 -- 'alexendersokolov/deepscientist-lite-codex-plugin (ds-lite)'
Manual alternative: copy the skill folder into ~/.claude/skills/ so Claude Code loads it on next launch.
cp -r -- 'alexendersokolov/deepscientist-lite-codex-plugin (ds-lite)' ~/.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
1324 findings · 195.1s
v0.3.74
36 findings · 129.7s
v0.1.0
11 findings · 40.9s
v0.1.0
2 findings · 41.0s
v1.4.0
None of the entry points this scanner reads were found in this artifact. What each scanner covers
0 findings · 0.2s
vv0.3.2
No Go packages were found in this artifact. What each scanner covers
0 findings · 0.1s
v0.1.0
This scanner found nothing in this artifact that it assesses. What each scanner covers
0 findings · 1.0s
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: completeagent-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 1,373 findings across every scanner that examined this package. None of the 92 findings rated critical by their scanner were dismissed.
Not reviewed is not the same as clean. Those 1,003 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.
68 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: SOCIAL_ENG_VAGUE_DESCRIPTION, MANIFEST_MISSING_LICENSE · Files: /repo/docs/SKILL.md, /repo/teaching/fixtures/SKILL.md, /repo/teaching/fixtures/evidence-review/SKILL.md and 31 more · reported by cisco-skill-scanner
2 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: SECRET_PASSWORD_VAR, GLOB_HIDDEN_FILE_TARGETING · Files: /repo/tests/test_communication_audit.py, /repo/tests/test_state_kernel.py · reported by cisco-skill-scanner
The model could have called any of these a false positive and did not.
254 MANIFEST_MISSING_LICENSE
Files: /repo/plugins/deepscientist-lite-knowledge/skills/ds-lite-knowledge/SKILL.md, /repo/plugins/deepscientist-lite-control-plane/skills/ds-lite-control-plane/SKILL.md, /repo/plugins/deepscientist-lite-engineering/skills/ds-lite-engineering/SKILL.md and 251 more · reported by cisco-skill-scanner
20 HIDDEN_DATA_FILE
Files: /repo/plugins/deepscientist-lite-knowledge/.codex-plugin/plugin.json, /repo/plugins/deepscientist-lite-control-plane/.codex-plugin/plugin.json, /repo/plugins/deepscientist-lite/.codex-plugin/plugin.json and 9 more · reported by cisco-skill-scanner
10 EXCESSIVE_FILE_COUNT
Files: /repo/plugins/deepscientist-lite/skills/nature-figure/., /repo/plugins/deepscientist-lite-academic/skills/nature-figure/., /repo/. and 7 more · reported by cisco-skill-scanner
10 MANIFEST_INVALID_NAME
Files: /repo/plugins/deepscientist-lite/vendor/nature-skills/91862221b39f7ca16d52ae0e1e9cb6c2bb31a96b/skills/nature-writing/static/fragments/paper_type/SKILL.md, /repo/plugins/deepscientist-lite/vendor/nature-skills/91862221b39f7ca16d52ae0e1e9cb6c2bb31a96b/skills/nature-polishing/static/fragments/paper_type/SKILL.md, /repo/plugins/deepscientist-lite/vendor/nature-skills/91862221b39f7ca16d52ae0e1e9cb6c2bb31a96b/skills/nature-paper2ppt/static/fragments/paper_type/SKILL.md and 7 more · reported by cisco-skill-scanner
2
794 The review call did not complete.
Rules: PATH_TRAVERSAL_OPEN, COMMAND_INJECTION_JS_CHILD_PROCESS, DATA_EXFIL_SOCKET_CONNECT and 22 more · Files: /repo/plugins/deepscientist-lite/vendor/nature-skills/91862221b39f7ca16d52ae0e1e9cb6c2bb31a96b/skills/nature-academic-search/scripts/format-converter.py, /repo/plugins/deepscientist-lite/skills/nature-academic-search/scripts/format-converter.py, /repo/plugins/deepscientist-lite-academic/skills/nature-academic-search/scripts/format-converter.py and 180 more · reported by cisco-skill-scanner, nerlo-behavioral, agent-audit-kit
209 The model called these false positives and our own check did not agree, so the dismissal was refused.
Rules: SECRET_PASSWORD_VAR, UNANALYZABLE_BINARY, SOCIAL_ENG_VAGUE_DESCRIPTION and 3 more · Files: /repo/teaching/offline_acceptance.py, /repo/plugins/deepscientist-lite/vendor/nature-skills/91862221b39f7ca16d52ae0e1e9cb6c2bb31a96b/skills/nature-figure/assets/figures4papers/figure_Cflows/figures/figX_comparison_Ablation.pdf, /repo/plugins/deepscientist-lite-academic/skills/nature-figure/assets/figures4papers/figure_Cflows/figures/fig2_comparison_Trajectory.pdf and 196 more · reported by cisco-skill-scanner, nerlo-install-instruction
Artifact enables shell execution, network egress, and file system access.
The artifact contains critical findings for shell execution, network egress, and file system access. Specifically, it has capabilities for command injection, dynamic code execution, path traversal, and direct socket connections. High severity findings also indicate potential for data exfiltration via file system access and network requests, along with credential exposure. These risks are present in various Python and JavaScript components of 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.
Files: plugins/deepscientist-lite/skills/nature-paper-to-patent/scripts/disclosure/package.json, plugins/deepscientist-lite-academic/skills/nature-paper-to-patent/scripts/disclosure/package.json · reported by agent-audit-kit
2 AAK-MCP-006
Files: plugins/deepscientist-lite/skills/nature-academic-search/config/mcp-snippet.json, plugins/deepscientist-lite-academic/skills/nature-academic-search/config/mcp-snippet.json · reported by agent-audit-kit
1 AAK-TASKS-003
Files: plugins/deepscientist-lite-core/scripts/ds_lite_task_router.py · reported by agent-audit-kit
1 LOW_ANALYZABILITY
Files: /repo/plugins/deepscientist-lite-web · reported by cisco-skill-scanner