AI Fleet Coordinator — Grok Bot seat skill packs
Multi-agent fleet protocols with dedicated Grok Bot [GB- ] seat skills for session-start, board ops, land, and housekeeper roles.
SafeScan verdict · score 56/100
- Coverage
- full
- Checks run
- Rule-based pattern scan
- Files checked
- 913
- 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 | 4 matched | |
| No executable scripts | 0/1 | 50 script file(s) of 913 | |
| 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.
- hides actions from the owner (tool-poisoning hallmark): "… section for the pattern that silently posts no gap and exits `0`. - It …"
- asks for overly broad permissions: "…ain (owner action, once, with sudo):** run `{ fleet-secrets get…"
- Contains ads/promo (affiliate, course or sponsor links): warning only
- Content SHA-256
- 9d288a09ae6fd44d…
- Commit
- daeeb54cc3
- Files
- .gitignore
.gitleaksignore
AGENTS.md
EFFORT-LOG-PROTOCOL.md
FLEET-PROTOCOL.md
FLEET-UI-COPY.md
+907
About
- Author
- jaywedgeworth22 ↗
- Listed on
- github:RongleCat/awesome-grok-bot ↗
- Category (approx.)
- agentops
- First seen
- 2026-10-30
- Last seen
- 2026-10-30
- URL
- github.com ↗