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.
1 critical finding reported by osv-scanner. The composite score alone does not reflect this — read the per-scanner reports below.
Choose your runtime: the CLI writes the mcpServers config entry for that target.
nerlo install --target claude-code -- spinybacked-orbweaver-eval
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.
v1.4.0
0 findings · 1.1s
v2.0.11
169 findings · 36.7s
v0.3.74
28 findings · 7.7s
v0.1.0
0 findings · 7.3s
v0.1.0
48 findings · 7.3s
v2.3.8
9 findings · 7.7s
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 · 2.0s
v0.71.0
No dependency manifest or lockfile was found in this artifact. What each scanner covers
0 findings · 0.3s
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
1 scan on record. Every scan's full results are retained immutably for 24 months.
| Completed | Composite | Change | Scanners | Status |
|---|---|---|---|---|
| Aug 22, 2026 | Flagged20 | — | agentshield: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·n/a: not applicablenerlo-multi-source ·n/a: not applicabletrivy ·n/a: not applicableosv-scanner: completetrivy_image ·n/a: not applicablegovulncheck ·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 254 findings across every scanner that examined this package. None of the 1 finding rated critical by their scanner were dismissed.
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.
31 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-005, opt.nerlo-rules.nerlo-install-destructive-system-command, opt.nerlo-rules.nerlo-install-pipe-to-shell and 6 more · Files: docs/research/v1-v2-journal-quality-analysis.md, /repo/docs/research/testing-infrastructure-research.md, /repo/evaluation/examples/instrumentation.js and 13 more · reported by agent-audit-kit, nerlo-install-instruction, cisco-skill-scanner
2 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-005 · Files: .claude/CLAUDE.md · 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.
60 MANIFEST_MISSING_LICENSE
Files: /repo/SKILL.md, /repo/prds/SKILL.md, /repo/.claude/SKILL.md and 57 more · reported by cisco-skill-scanner
60 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/prds/SKILL.md, /repo/.claude/SKILL.md and 57 more · reported by cisco-skill-scanner
27 opt.nerlo-rules.nerlo-install-shell-inline-command
Files: /repo/README.md, /repo/evaluation/javascript/release-it/run-2/lessons-for-run3.md, /repo/evaluation/javascript/release-it/run-3/lessons-for-run4.md and 16 more · reported by nerlo-install-instruction
14 AAK-HEALTHCARE-AI-004
Files: prds/115-evaluation-run-22.md, prds/153-evaluation-run-27.md, prds/done/140-evaluation-run-25.md and 11 more · reported by agent-audit-kit
12 PIPELINE_TAINT_FLOW
Files: /repo/journal/entries/2026-02/2026-02-10.md, /repo/journal/summaries/daily/2026-02-10.md, /repo/journal/summaries/daily/SKILL.md and 1 more · reported by cisco-skill-scanner
9 opt.nerlo-rules.nerlo-install-run-bundled-artifact
Files: /repo/evaluation/javascript/commit-story-v2/run-20/per-file-sections/git-collector.js.md, /repo/evaluation/javascript/commit-story-v2/run-25/failure-deep-dives.md, /repo/evaluation/typescript/taze/run-13/pr-evaluation.md and 2 more · reported by nerlo-install-instruction
8 opt.nerlo-rules.nerlo-install-pipe-to-shell
Files: /repo/journal/entries/2026-02/2026-02-10.md, /repo/journal/summaries/daily/2026-02-10.md, /repo/prds/done/25-autonomous-dev-infrastructure.md · reported by nerlo-install-instruction
4 AAK-IPI-WILD-CORPUS-001
Files: prds/32-evaluation-run-11.md, evaluation/javascript/commit-story-v2/run-10/actionable-fix-output.md, evaluation/javascript/commit-story-v2/run-10/lessons-for-prd11.md and 1 more · reported by agent-audit-kit
4 AAK-MCP-018
Files: evaluation/javascript/commit-story-v2/run-17/debug-dumps/src/mcp/tools/reflection-tool.js, evaluation/javascript/commit-story-v2/run-17/debug-dumps/src/mcp/tools/context-capture-tool.js, evaluation/javascript/commit-story-v2/run-16/debug-dumps/src/mcp/tools/reflection-tool.js and 1 more · reported by agent-audit-kit
4 FILE_MAGIC_MISMATCH
Files: /repo/evaluation/javascript/commit-story-v2/run-26/parse-log.sh · reported by cisco-skill-scanner
3 EXCESSIVE_FILE_COUNT
Files: /repo/evaluation/., /repo/evaluation/javascript/commit-story-v2/., /repo/. · reported by cisco-skill-scanner
3 LOW_ANALYZABILITY
Files: /repo/evaluation/is, /repo/evaluation/javascript/commit-story-v2/run-16, /repo/evaluation/javascript/commit-story-v2/run-17 · reported by cisco-skill-scanner
1 AAK-LEGAL-002
Files: package.json · reported by agent-audit-kit
1 GHSA-28wg-ghj8-5hjv
Files: /repo/package-lock.json · reported by osv-scanner
1 GHSA-2v37-7h3g-55p8
Files: /repo/package-lock.json · reported by osv-scanner
1 GHSA-5xrq-8626-4rwp
Files: /repo/package-lock.json · reported by osv-scanner
1 GHSA-6g55-p6wh-862q
Files: /repo/package-lock.json · reported by osv-scanner
1 GHSA-fx2h-pf6j-xcff
Files: /repo/package-lock.json · reported by osv-scanner
1 GHSA-fxqj-rqcc-2cmp
Files: /repo/package-lock.json · reported by osv-scanner
1 GHSA-g7r4-m6w7-qqqr
Files: /repo/package-lock.json · reported by osv-scanner
1 GHSA-r28c-9q8g-f849
Files: /repo/package-lock.json · reported by osv-scanner
1 GHSA-v6wh-96g9-6wx3
Files: /repo/package-lock.json · reported by osv-scanner
1 HIDDEN_DATA_FILE
Files: /repo/.vals.yaml · reported by cisco-skill-scanner
1 MANIFEST_INVALID_NAME
Files: /repo/.claude/SKILL.md · reported by cisco-skill-scanner
1 opt.nerlo-rules.nerlo-install-destructive-system-command
Files: /repo/prds/done/25-autonomous-dev-infrastructure.md · reported by nerlo-install-instruction
Critical vulnerability and high-risk shell execution detected.
A critical vulnerability (GHSA-5xrq-8626-4rwp) is present in a dependency listed in `/repo/package-lock.json`. The artifact also contains multiple instances of high-severity pipeline taint flow in journal and skill files, which could lead to data compromise. Furthermore, several files, including journal entries and PRD documents, contain instructions that pipe data directly to a shell for execution or involve destructive system commands. These capabilities warrant immediate attention due to the potential for system compromise and data manipulation.
Concern level assessed by the review: Critical. This is the review's scale, not the registry badge.
Showing 25 of 31; the rest are in the per-scanner reports above.
Reviewed by gemini-2.5-flash. The model sees the findings, not your code, and cannot change a score.