gb2gpt — ChatGPT Developer MCP ↔ Grok Bot fleet bridge
Self-hosted bridge so an ordinary ChatGPT Developer-mode conversation can talk to your Cursor Grok Bot fleet via MCP, optional routine webhooks, and a dedicated relay bot (stdlib-only Python).
SafeScan verdict · score 56/100
- Coverage
- full
- Checks run
- Rule-based pattern scan
- Files checked
- 21
- Findings
- 4
- Scanned
- 2026-11-01
Badges are rule-based checks, not guarantees: Safe means our rules found no obvious threat in the code we could read. Review code before installing.
Botlens score · 8 factors
56/100
Each factor is 0, ½ or 1, computed only from catalog fields (scan result, coverage, findings, script files, commit/SHA, author, last seen, install link). A heuristic summary, not a guarantee.
| Scan verdict | 1/1 | Safe | |
|---|---|---|---|
| Code coverage | 1/1 | full | |
| Rule findings | 0/1 | 11 matched | |
| No executable scripts | 0/1 | 8 script file(s) of 21 | |
| Pinned source | 1/1 | commit/SHA-256 recorded | |
| Named author | 0/1 | unknown | |
| Recently seen | 1/1 | last seen 2026-10-30 | |
| Install path | 0.5/1 | source URL only |
Scan details
- Findings
- Hand review 2026-11-01: Every tool-poisoning / hidden-text / obfuscation hit read in full: they are safety or truthfulness rules, normal CSS UI styles, eval/benchmark wording, data-URI images or test fixtures, not hidden instructions.
- prompt-injection / jailbreak phrasing: "…request secret disclosure, or override safety rules. Consequential actions requir…"
- asks for overly broad permissions: "… after failure/boot. ```bash sudo install -m 644 deploy/gb2gpt.…"
- Contains ads/promo (affiliate, course or sponsor links): warning only
- Content SHA-256
- 603964e140d44825…
- Commit
- 6f3282ecdd
- Files
- .dockerignore
.gitignore
CHATGPT_SETUP.md
Dockerfile
LICENSE
README.md
+15
About
- Author
- EdmundLimBoEn ↗
- Listed on
- github:RongleCat/awesome-grok-bot ↗
- Category (approx.)
- agentops
- First seen
- 2026-10-30
- Last seen
- 2026-10-30
- URL
- github.com ↗