Grok Custom Skills (89-pack for ~/.grok/skills)
Curated library of 89 safety-conscious skill packages installable into ~/.grok/skills for Grok-compatible agent hosts.
Caution: review the findings below before installing.
CautionScan verdict · score 50/100
- Coverage
- full
- Checks run
- Rule-based pattern scan
- Files checked
- 204
- 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
50/100
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 | 0.5/1 | Caution | |
|---|---|---|---|
| Code coverage | 1/1 | full | |
| Rule findings | 0/1 | 7 matched | |
| No executable scripts | 0/1 | 29 script file(s) of 204 | |
| 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: Triage: makes outbound API calls (to its own or configured services). Credential-source sweep (browser cookies, Keychain, app token files, exfil hosts) found nothing; no evidence of data theft in the stored content.
- sends or posts automatically without approval: "…ater and HITL gates. Use for: auto reply WhatsApp, enable WhatsApp ass…"
- asks for overly broad permissions: "…| **admin** | Administrator | Full access to all resources | | **super_…"
- Contains ads/promo (affiliate, course or sponsor links): warning only
- Content SHA-256
- e61b414726f678b0…
- Commit
- bf31cc83a4
- Files
- .gitignore
.markdownlint.json
.pre-commit-config.yaml
CHANGELOG.md
CODE_OF_CONDUCT.md
CONTRIBUTING.md
+198
About
- Author
- Stijnman ↗
- Listed on
- github:RongleCat/awesome-grok-bot ↗
- Category (approx.)
- agentops
- First seen
- 2026-10-30
- Last seen
- 2026-10-30
- URL
- github.com ↗