Loading the registry…
AI agent skills for building confidential dApps with the Zama Protocol (fhEVM) — Claude Code plugin + npx fallback
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.
21 critical findings reported by cisco-skill-scanner, 17 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/kocaemre/zama-skills, 185 findings
Claude Skills install to a single target, no runtime picker.
nerlo install -- zama-skills
Manual alternative: copy the skill folder into ~/.claude/skills/ so Claude Code loads it on next launch.
cp -r -- zama-skills ~/.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
3 findings · 0.8s
v2.0.11
82 findings · 15.6s
v0.3.74
24 findings · 8.0s
v0.1.0
1 finding · 7.6s
v0.1.0
4 findings · 7.6s
v0.1.0
0 findings · 11.3s
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 21, 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 114 findings across every scanner that examined this package. 4 of 21 findings rated critical by their scanner were among the dismissals.
Not reviewed is not the same as clean. Those 2 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.
22 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-002, agents-comment-injection-18240, agents-comment-injection-0 and 3 more · Files: CLAUDE.md · reported by agent-audit-kit, agentshield
14 Documentation or example — The match is in documentation or sample code, confirmed by our own check to be outside the installed artifact.
Rules: LOW_ANALYZABILITY, AAK-LEGAL-002, HIDDEN_DATA_FILE and 5 more · Files: /repo/examples/confidential-token, examples/confidential-token/package.json, examples/confidential-token/packages/contracts/package.json and 7 more · reported by cisco-skill-scanner, agent-audit-kit, nerlo-behavioral
7 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, DATA_EXFIL_JS_FS_ACCESS, LOW_ANALYZABILITY · Files: /repo/scripts/validate.test.ts, /repo/tests/integration/zama-init-smoke.test.ts, /repo/scripts/generate-generic-docs.test.mjs and 2 more · reported by cisco-skill-scanner
1 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 · Files: .github/workflows/ci.yml · 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.
15 MANIFEST_MISSING_LICENSE
Files: /repo/plugins/zama-skills/skills/init/SKILL.md, /repo/plugins/zama-skills/skills/frontend/SKILL.md, /repo/plugins/zama-skills/skills/design/SKILL.md and 12 more · reported by cisco-skill-scanner
10 COMMAND_INJECTION_EVAL
Files: /repo/plugins/zama-skills/skills/deploy/scripts/deploy.ts, /repo/plugins/zama-skills/skills/init/scripts/scaffold.ts · reported by cisco-skill-scanner
9 LOW_ANALYZABILITY
Files: /repo/plugins/zama-skills/skills/contract, /repo/plugins/zama-skills/skills/audit, /repo/plugins/zama-skills/skills/autonomous and 6 more · reported by cisco-skill-scanner
7 COMMAND_INJECTION_JS_CHILD_PROCESS
Files: /repo/plugins/zama-skills/skills/init/scripts/preflight.ts, /repo/bin/zama-skills.mjs, /repo/plugins/zama-skills/skills/_lib/preflight-shared.ts and 2 more · reported by cisco-skill-scanner
6 SOCIAL_ENG_VAGUE_DESCRIPTION
Files: /repo/plugins/zama-skills/skills/debug/SKILL.md, /repo/SKILL.md, /repo/plugins/zama-skills/shared/SKILL.md and 3 more
2 The model called these false positives and our own check did not agree, so the dismissal was refused.
Rules: HIDDEN_DATA_FILE · Files: /repo/plugins/zama-skills/skills/init/assets/templates/.env.example.tpl · reported by cisco-skill-scanner
Critical command injection and shell execution risks identified
The artifact contains multiple critical command injection vulnerabilities, specifically allowing shell execution via `eval` and `child_process` in several scripts, including `/repo/bin/zama-skills.mjs` and `/repo/plugins/zama-skills/skills/deploy/scripts/deploy.ts`. Additionally, there are high severity findings related to potential data exfiltration through file system access and the use of unapproved tools. These capabilities could lead to unauthorized system access or data manipulation.
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.
5 ALLOWED_TOOLS_GREP_VIOLATION
Files: /repo/plugins/zama-skills/skills/doctor/repo/plugins/zama-skills/skills/doctor/SKILL.md, /repo/plugins/zama-skills/skills/init/repo/plugins/zama-skills/skills/init/SKILL.md, /repo/plugins/zama-skills/skills/contract/repo/plugins/zama-skills/skills/contract/SKILL.md and 2 more · reported by cisco-skill-scanner
4 ALLOWED_TOOLS_WRITE_VIOLATION
Files: /repo/plugins/zama-skills/skills/design/repo/plugins/zama-skills/skills/design/SKILL.md, /repo/plugins/zama-skills/skills/deploy/repo/plugins/zama-skills/skills/deploy/SKILL.md, /repo/plugins/zama-skills/skills/init/repo/plugins/zama-skills/skills/init/SKILL.md and 1 more · reported by cisco-skill-scanner
4 opt.nerlo-rules.nerlo-install-run-bundled-artifact
Files: /repo/generic/doctor.md, /repo/plugins/zama-skills/skills/audit/scripts/lib/deprecation-grep.ts, /repo/plugins/zama-skills/skills/doctor/SKILL.md · reported by nerlo-install-instruction
3 DATA_EXFIL_JS_FS_ACCESS
Files: /repo/scripts/validate.ts · reported by cisco-skill-scanner
2 HIDDEN_DATA_FILE
Files: /repo/plugins/zama-skills/skills/init/assets/templates/.gitignore.tpl · reported by cisco-skill-scanner
1 AAK-MARKETPLACE-001
Files: .claude-plugin/marketplace.json · reported by agent-audit-kit
1 ALLOWED_TOOLS_BASH_VIOLATION
Files: /repo/plugins/zama-skills/skills/doctor/repo/plugins/zama-skills/skills/doctor/SKILL.md · reported by cisco-skill-scanner
1 EXCESSIVE_FILE_COUNT
Files: /repo/. · reported by cisco-skill-scanner
Showing 25 of 30; the rest are in the per-scanner reports above.