Moe's Tavern — IDE task board including Grok Build
AI agent task board for Claude Code, Codex, Gemini CLI, and Grok Build with plan/approve/build/review flows and .moe/ state in-repo.
SafeScan verdict · score 56/100
- Coverage
- full
- Checks run
- Rule-based pattern scan
- Files checked
- 511
- Findings
- 3
- 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 | 3 matched | |
| No executable scripts | 0/1 | 37 script file(s) of 511 | |
| 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.
- obfuscated / encoded code: "…"forbiddenPatterns": [ "eval(", "innerHTML", "d…"
- hides actions from the owner (tool-poisoning hallmark): "…ected.\n - An npm gate would silently run with no dependency phase and …"
- Content SHA-256
- b2c0293ab571f668…
- Commit
- 1b59ad8d11
- Files
- .gitattributes
.gitignore
2026-10-24-ai-code-quality-and-context.md
AGENTS.md
CLAUDE.md
CODE_OF_CONDUCT.md
+505
About
- Author
- yaront1111 ↗
- Listed on
- github:RongleCat/awesome-grok-bot ↗
- Category (approx.)
- productivity
- First seen
- 2026-10-30
- Last seen
- 2026-10-30
- URL
- github.com ↗