Loading the registry…
The single orchestrator that drives a story from spec to pull request, in one of three modes: `afk` (never stops), `intelligent` (stops only for a genuine open question — this is cloud's default behavior), or `gated` (intelligent's question gate plus configurable phase-boundary stops). It is state-driven: it reads the session checkpoint and runs every remaining stage in the same canonical order. All three modes run every stage back-to-back to the pull request; they differ only in whether, and where, the pipeline pauses for a human. Output is milestone-only. Activates on "arcus <STORY>" (default), "plan <STORY>" → gated; "arcus <STORY> --intelligent" → intelligent; "forge <STORY>", "afk <STORY>", "run afk on <STORY>", or "arcus <STORY> --afk" → afk; "resume <STORY>" → continue from the first incomplete stage in whatever mode the checkpoint persists.
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.
github_release: https://github.com/piyushbhargava1412/arcus-plugin, 0 findings
Claude Skills install to a single target, no runtime picker.
nerlo install -- 'piyushbhargava1412/arcus-plugin (arcus-controller)'
Manual alternative: copy the skill folder into ~/.claude/skills/ so Claude Code loads it on next launch.
cp -r -- 'piyushbhargava1412/arcus-plugin (arcus-controller)' ~/.claude/skills/
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
102 findings · 10.4s
v0.3.74
4 findings · 2.2s
v0.1.0
0 findings · 3.7s
v0.1.0
27 findings · 3.7s
v0.1.0
0 findings · 7.7s
v2.3.8
15 findings · 7.0s
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
v0.71.0
No dependency manifest or lockfile was found in this artifact. What each scanner covers
0 findings · 0.2s
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 21, 2026 | Flagged26 | — | agentshield ·n/a: not applicablecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·n/a: not applicablenerlo-multi-source: completetrivy ·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 148 findings across every scanner that examined this package.
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.
41 MANIFEST_MISSING_LICENSE
Files: /repo/plugins/arcus/skills/write-evals/SKILL.md, /repo/plugins/arcus/skills/model-strategy/SKILL.md, /repo/plugins/arcus/skills/arcus-guide/SKILL.md and 38 more · reported by cisco-skill-scanner
32 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/site/SKILL.md, /repo/site/concepts/SKILL.md and 29 more · reported by cisco-skill-scanner
24 PIPELINE_TAINT_FLOW
Files: /repo/plugins/arcus-opencode/install.sh, /repo/plugins/arcus/skills/arcus-guide/assets/faq.md, /repo/plugins/arcus-opencode/INSTALL.md and 6 more · reported by cisco-skill-scanner
13 opt.nerlo-rules.nerlo-install-run-bundled-artifact
Files: /repo/CHANGELOG.md, /repo/plugins/arcus/skills/arcus-controller/references/brainstorm.md, /repo/plugins/arcus/skills/arcus-controller/references/closure.md and 5 more · reported by nerlo-install-instruction
11 opt.nerlo-rules.nerlo-install-pipe-to-shell
Files: /repo/CHANGELOG.md, /repo/README.md, /repo/plugins/arcus-opencode/INSTALL.md and 3 more · reported by nerlo-install-instruction
3 opt.nerlo-rules.nerlo-install-fetch-raw-then-run
Files: /repo/README.md, /repo/plugins/arcus/skills/arcus-guide/assets/faq.md · reported by nerlo-install-instruction
2 FILE_MAGIC_MISMATCH
Files: /repo/site/.vitepress/theme/index.ts · reported by cisco-skill-scanner
2 LOW_ANALYZABILITY
Files: /repo/plugins/arcus-opencode, /repo/site · reported by cisco-skill-scanner
1 AAK-HEALTHCARE-AI-004
Files: plugins/arcus/skills/arcus-guide/SKILL.md · reported by agent-audit-kit
1 AAK-IPI-WILD-CORPUS-001
Files: plugins/arcus/skills/code-reviewer/SKILL.md · reported by agent-audit-kit
1 AAK-LEGAL-002
Files: site/package.json · reported by agent-audit-kit
1 AAK-MARKETPLACE-001
Files: .claude-plugin/marketplace.json · reported by agent-audit-kit
1 EXCESSIVE_FILE_COUNT
Files: /repo/. · reported by cisco-skill-scanner
1 GHSA-28wg-ghj8-5hjv
Files: /repo/site/pnpm-lock.yaml · reported by osv-scanner
1 GHSA-2v37-7h3g-55p8
Files: /repo/site/pnpm-lock.yaml · reported by osv-scanner
1 GHSA-2v8p-3f2j-5mp7
Files: /repo/site/pnpm-lock.yaml · reported by osv-scanner
1 GHSA-3rrr-jr9j-h3q3
Files: /repo/site/pnpm-lock.yaml · reported by osv-scanner
1 GHSA-4w7w-66w2-5vf9
Files: /repo/site/pnpm-lock.yaml · reported by osv-scanner
1 GHSA-55q2-fjhq-7xh7
Files: /repo/site/pnpm-lock.yaml · reported by osv-scanner
1 GHSA-67mh-4wv8-2f99
Files: /repo/site/pnpm-lock.yaml · reported by osv-scanner
1 GHSA-6x64-9x62-f2gx
Files: /repo/site/pnpm-lock.yaml · reported by osv-scanner
1 GHSA-c2j3-45gr-mqc4
Files: /repo/site/pnpm-lock.yaml · reported by osv-scanner
1 GHSA-c4c3-pg64-4m4v
Files: /repo/site/pnpm-lock.yaml · reported by osv-scanner
1 GHSA-fx2h-pf6j-xcff
Files: /repo/site/pnpm-lock.yaml · reported by osv-scanner
1 GHSA-fxqj-rqcc-2cmp
Files: /repo/site/pnpm-lock.yaml · reported by osv-scanner
1 GHSA-r28c-9q8g-f849
Files: /repo/site/pnpm-lock.yaml · reported by osv-scanner
1 GHSA-rhh3-jpg6-66xh
Files: /repo/site/pnpm-lock.yaml · reported by osv-scanner
1 GHSA-v6wh-96g9-6wx3
Files: /repo/site/pnpm-lock.yaml · reported by osv-scanner
Shell execution and unanalyzed code present high risks.
The artifact contains multiple high-severity findings related to shell execution, including piping content directly to a shell and fetching raw content for execution. Several components exhibit pipeline taint flow, indicating potential for data manipulation or command injection. Additionally, portions of the code are of low analyzability, hindering comprehensive security assessment.
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.
Showing 25 of 35; the rest are in the per-scanner reports above.