davidondrej new-grok-bot design skill

David Ondrej agent-skills pack including new-grok-bot: unit-of-work test then one paste-ready prompt for creating a Grok Bot teammate.

View source ↗
SafeScan verdict · score 56/100
Coverage
full
Checks run
Rule-based pattern scan
Files checked
143
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.

View source ↗
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 verdict1/1Safe
Code coverage1/1full
Rule findings0/112 matched
No executable scripts0/18 script file(s) of 143
Pinned source1/1commit/SHA-256 recorded
Named author0/1unknown
Recently seen1/1last seen 2026-10-30
Install path0.5/1source URL only

Scan details

Findings
  • Hand review 2026-11-01: Keychain command is a guard-hook test case (hooks/test-guard.sh:120); cli-config is an allowlist note.
  • reads sensitive local files (keys, .env, cookies): "…ees start with tracked files. Include required untracked files such as `.env` through the repo's `.worktre…"
  • asks for overly broad permissions: "…x && brew install --cask cmux sudo ln -sf /Applications/cmux.app…"
  • asks for overly broad permissions: "…rtifact. It installs without `sudo` or a global npm configurat…"
Content SHA-256
75611a53ed5fc730…
Commit
d5e3a3aa53
Files
.gitignore
AGENTS.md
LICENSE
README.md
hooks/deny-dangerous.sh
hooks/test-guard.sh
+137

About

Author
davidondrej ↗
Listed on
github:RongleCat/awesome-grok-bot ↗
Category (approx.)
agentops
First seen
2026-10-30
Last seen
2026-10-30
URL
github.com ↗
Get the Botlens skill