Loading the registry…
Shared memory, impact analysis, and guardrail hooks for AI coding agents — authored once, emitted as native config for Claude Code, Codex, Cursor, Gemini, Aider, and more.
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.
13 critical findings reported by cisco-skill-scanner, agent-audit-kit, 8 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/CodeWithJuber/forgekit, 616 findings
Choose your runtime: the CLI writes the mcpServers config entry for that target.
nerlo install --target claude-code -- @codewithjuber/forgekit
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
Incomplete run
1 finding · 1.1s
v2.0.11
138 findings · 28.3s
v0.3.74
23 findings · 18.5s
v0.1.0
4 findings · 15.2s
v0.1.0
7 findings · 15.2s
v0.1.0
0 findings · 16.9s
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 ·!: incompletecisco-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 173 findings across every scanner that examined this package. 5 of 13 findings rated critical by their scanner were among the dismissals.
Not reviewed is not the same as clean. Those 79 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.
40 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, opt.nerlo-rules.nerlo-install-pipe-to-shell, AAK-HEALTHCARE-AI-004 and 7 more · Files: /repo/docs/legacy/RECONCILE.md, /repo/docs/legacy/SKILL.md, docs/GUIDE.md and 14 more · reported by cisco-skill-scanner, nerlo-install-instruction, agent-audit-kit
20 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: AAK-SECRET-002, SECRET_GITHUB_TOKEN, AAK-SECRET-008 and 3 more · Files: test/knowledge_router.test.js, test/deja.test.js, /repo/test/guards.test.js and 12 more · reported by agent-audit-kit, cisco-skill-scanner
3 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-GHA-IMMUTABLE-001, MANIFEST_INVALID_NAME · Files: .github/workflows/labels.yml, .github/workflows/scorecard.yml, /repo/.github/SKILL.md · reported by agent-audit-kit, cisco-skill-scanner
The model could have called any of these a false positive and did not.
8 DATA_EXFIL_JS_NETWORK
Files: /repo/landing/assets/index-Bzzxm3eY.js, /repo/landing/assets/index-CLPL-LNO.js, /repo/landing/assets/index-CYpd6266.js and 4 more · reported by cisco-skill-scanner
7 COMMAND_INJECTION_JS_CHILD_PROCESS
Files: /repo/src/adjudicate.js, /repo/src/embed.js, /repo/src/gateway_model_map.js and 3 more · reported by cisco-skill-scanner
6 AAK-SECRET-004
Files: src/predictor.js, global/guards/protect-paths.sh, landing/assets/v-react-fNML7Qzi.js and 2 more · reported by agent-audit-kit
4 DATA_EXFIL_JS_FS_ACCESS
Files: /repo/scripts/bump.mjs · reported by cisco-skill-scanner
3 opt.nerlo-rules.nerlo-js-secret-to-network-egress
Files: /repo/landing/assets/index-Bzzxm3eY.js, /repo/landing/assets/index-CLPL-LNO.js, /repo/landing/assets/index-CYpd6266.js · reported by nerlo-behavioral
1 EXCESSIVE_FILE_COUNT
Files: /repo/. · reported by cisco-skill-scanner
1 LOW_ANALYZABILITY
Files: /repo · reported by cisco-skill-scanner
1 opt.nerlo-rules.nerlo-py-dynamic-exec
Files: /repo/research/python-prototypes/router_gate/router_gate/executors.py · reported by nerlo-behavioral
62 The model called these false positives and our own check did not agree, so the dismissal was refused.
Rules: AAK-SECRET-008, PIPELINE_TAINT_FLOW, opt.nerlo-rules.nerlo-install-pipe-to-shell and 13 more · Files: .gitleaks.toml, /repo/mintlify/installation.mdx, /repo/ARCHITECTURE.md and 51 more · reported by agent-audit-kit, cisco-skill-scanner, nerlo-install-instruction and 1 more
17 The model did not answer for these findings.
Rules: SOCIAL_ENG_VAGUE_DESCRIPTION · Files: /repo/SKILL.md, /repo/reports/SKILL.md, /repo/global/SKILL.md and 14 more · reported by cisco-skill-scanner
Critical command injection and credential exposure.
The artifact contains critical command injection vulnerabilities in JavaScript files such as `adjudicate.js` and `llm.js`, enabling shell execution. It also exposes credentials in `.gitleaks.toml` and other source files. Further findings indicate network egress with secrets and dynamic code execution in Python components.
Concern level assessed by the review: Critical. This is the review's scale, not the registry badge.
Showing 15 of 15; 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.