ClawAudit verdict
minigame-i18n
A WeChat mini-game localization workflow that orchestrates sub-skills for scanning Chinese text, generating language packs, and applying text/image replacements — all local file operations and npm installs within a developer's project, with no external data exfiltration.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
Permission integrity
package_install
Findings (5)
<script> tag in markdown — potential code injection
scripts/scan-chinese.js · prose · downgraded · <script>
References child_process — can spawn system processes
scripts/replace-text.js · prose · downgraded · child_process
Uses exec() — may execute shell commands
scripts/replace-text.js · prose · downgraded · exec(
String.fromCharCode — can build strings to evade detection
references/scan-analysis.md · prose · downgraded · String.fromCharCode
Node http/https module — low-level network access
scripts/upload-images.js · prose · downgraded · require('http')
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
No declared permissions — minimal attack surface.
package_install Is this flag fair?
Thanks — recorded.