Loading the registry…
Interactive CLI to install Claude Code harness modules (Workflow, Skills, Recommended Skills, Plugins)
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.
111 critical findings reported by cisco-skill-scanner, agent-audit-kit, nerlo-multi-source, 50 of them in the installed artifact. The composite score alone does not reflect this — read the per-scanner reports below.
This artifact ships from 3 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/ben2pc/auriga-cli, 887 findings
Claude Skills install to a single target, no runtime picker.
nerlo install -- auriga-cli
Manual alternative: copy the skill folder into ~/.claude/skills/ so Claude Code loads it on next launch.
cp -r -- auriga-cli ~/.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.
v1.4.0
5 findings · 1.0s
v2.0.11
753 findings · 26.2s
v0.3.74
27 findings · 11.1s
v0.1.0
0 findings · 7.5s
v0.1.0
11 findings · 7.5s
v0.1.0
2 findings · 19.6s
vv0.3.2
No Go packages were found in this artifact. What each scanner covers
0 findings · 0.1s
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: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·n/a: not applicablenerlo-multi-source: complete | 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 798 findings across every scanner that examined this package. 61 of 111 findings rated critical by their scanner were among the dismissals.
Not reviewed is not the same as clean. Those 157 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.
381 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: COMMAND_INJECTION_JS_CHILD_PROCESS, YARA_command_injection_generic, COMMAND_INJECTION_JS_FUNCTION_CONSTRUCTOR and 3 more · Files: /repo/tests/commit-reminder.test.mjs, /repo/tests/e2e-install.test.ts, /repo/tests/entrypoint.test.ts and 63 more · reported by cisco-skill-scanner
43 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: PIPELINE_TAINT_FLOW, MANIFEST_MISSING_LICENSE · Files: /repo/docs/architecture/SKILL.md, /repo/docs/architecture/auriga-cli-dev-guide.md, /repo/tests/fixtures/state/workflow-installed/SKILL.md and 37 more · reported by cisco-skill-scanner
2 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: AAK-AGENT-TRUST-002 · Files: .github/workflows/claude-code-review.yml, .github/workflows/claude.yml · reported by agent-audit-kit
The model could have called any of these a false positive and did not.
80 DATA_EXFIL_JS_FS_ACCESS
Files: /repo/plugins/auriga-workflow/skills/session-compound/analyzers/skill-catalog.mjs, /repo/plugins/auriga-workflow/skills/session-compound/scripts/insights-pipeline.mjs, /repo/plugins/auriga-workflow/skills/session-compound/scripts/render-report.mjs and 12 more · reported by cisco-skill-scanner
46 MANIFEST_MISSING_LICENSE
Files: /repo/plugins/quality-gate-scaffolder/skills/scaffold-python-backend-quality-gates/SKILL.md, /repo/plugins/quality-gate-scaffolder/skills/scaffold-typescript-frontend-quality-gates/SKILL.md, /repo/plugins/quality-gate-scaffolder/skills/scaffold-kotlin-android-quality-gates/SKILL.md and 43 more · reported by cisco-skill-scanner
24 COMMAND_INJECTION_JS_CHILD_PROCESS
Files: /repo/plugins/auriga-notify/scripts/notify.mjs, /repo/plugins/auriga-workflow/scripts/commit-reminder.mjs, /repo/plugins/auriga-workflow/scripts/pr-create-guard.mjs and 4 more · reported by cisco-skill-scanner
23 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/SKILL.md, /repo/ui/SKILL.md, /repo/.agents/SKILL.md and 20 more · reported by cisco-skill-scanner
19 COMMAND_INJECTION_EVAL
Files:
118 The review call did not complete.
Rules: agents-comment-injection-0, HIDDEN_EXECUTABLE_SCRIPT, AAK-IPI-WILD-CORPUS-001 and 17 more · Files: CLAUDE.md, /repo/.agents/skills/planning-with-files/scripts/resolve-plan-dir.sh, /repo/.agents/skills/planning-with-files/scripts/init-session.sh and 47 more · reported by agentshield, cisco-skill-scanner, agent-audit-kit and 1 more
32 The model called these false positives and our own check did not agree, so the dismissal was refused.
Rules: YARA_credential_harvesting_generic, AAK-SKILL-001, AAK-MARKETPLACE-001 and 3 more · Files: /repo/plugins/auriga-workflow/scripts/pr-merge-guard.mjs, .agents/skills/playwright-cli/SKILL.md, .cursor-plugin/marketplace.json and 21 more · reported by cisco-skill-scanner, agent-audit-kit, nerlo-install-instruction
7 The model did not answer for these findings.
Rules: DATA_EXFIL_JS_FS_ACCESS, MANIFEST_INVALID_NAME · Files: /repo/plugins/auriga-workflow/skills/session-compound/analyzers/claude-code.mjs, /repo/plugins/auriga-workflow/skills/session-compound/analyzers/codex.mjs, /repo/.agents/SKILL.md · reported by cisco-skill-scanner
Critical command injection and credential access risks
The artifact contains critical command injection vulnerabilities, enabling shell execution through child processes in workflow scripts and via `eval` functions. Critical findings also indicate potential credential harvesting in a PR merge guard script and secret exfiltration over the network. Additionally, high severity findings show extensive file system access for data exfiltration and the presence of hidden executable scripts. Numerous medium severity findings point to general network egress capabilities.
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.
11 HIDDEN_DATA_FILE
Files: /repo/plugins/session-instructions-loader/.codex-plugin/plugin.json, /repo/plugins/quality-gate-scaffolder/.codex-plugin/plugin.json, /repo/plugins/auriga-workflow/.codex-plugin/plugin.json and 7 more · reported by cisco-skill-scanner
4 LOW_ANALYZABILITY
Files: /repo/plugins/auriga-workflow/skills/session-compound, /repo/plugins/session-instructions-loader, /repo/plugins/auriga-workflow and 1 more · reported by cisco-skill-scanner
3 AAK-TAINT-001
Files: src/server.ts · reported by agent-audit-kit
1 AAK-LEGAL-002
Files: ui/package.json · reported by agent-audit-kit
1 ALLOWED_TOOLS_READ_VIOLATION
Files: /repo/.agents/skills/planning-with-files/repo/.agents/skills/planning-with-files/SKILL.md · reported by cisco-skill-scanner
1 HIDDEN_EXECUTABLE_SCRIPT
Files: /repo/.agents/skills/planning-with-files/scripts/check-complete.sh · reported by cisco-skill-scanner
1 nerlo-malware-obfuscated_blob
Files: github_release:ui-bundle.tar.gz.extracted/assets/index-BGfuCR9P.css · reported by nerlo-malware
1 opt.nerlo-rules.nerlo-js-secret-to-network-egress
Files: github_release:/tmp/nerlo-acquire/release/ui-bundle.tar.gz.extracted/assets/index-DI04gYPJ.js · reported by nerlo-provenance
Showing 25 of 25; the rest are in the per-scanner reports above.