Skills/ClawHub/anyskill

anyskill@1.0.7

CAUTION· static only

Publisher claims: "AnySkill — your private skill cloud. Manage, sync, and dynamically load agent skills from a GitHub-backed repository. Search cloud skills by natural language..." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher lanyijianke · publishing for 259 daysInstalls 1,404Last detonated 1 h ago

Coverage

Static only; nothing was run yet.

The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-18 and scored it 57/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Direct script execution from GitHub raw URL; Prompting user to enter sensitive credentials; Persistent behavior change attempt. Summary: static analysis only — behavior not yet observed.

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.

Static findings

HIGH
Direct script execution from GitHub raw URLSKILL.md:430 · Direct script execution from GitHub raw URL — unverified code source- Check if `{localPath}/generate-index.js` exists; if not, download from template repo: `https://raw.githubusercontent.com/lanyijianke/AnySkill/main/generate-index.js`Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Prompting user to enter sensitive credentialsSKILL.md:165 · Prompting user to enter sensitive credentials — social engineering> **A) I have a repo** — Just provide your Token and repo name:Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
MEDIUM
File type combined with upload actionSKILL.md:23 · File type combined with upload action — agent may exfiltrate local data files…ite` permission only. The token is used to: clone the private repo, fetch `index.json`, commit new/updated skills, and push changes. A read-only token will work for loading/searching skills but not for upload/sync operations. **Config file…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Persistent behavior change attemptSKILL.md:296 · Persistent behavior change attempt> From now on, you can load, download, and publish skills from any project.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Instructs the agent to modify its persistent memory or instruction filesSKILL.md:332 · Instructs the agent to modify its persistent memory or instruction files**Step 2: Append to `AGENTS.md`**Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Access to sensitive file pathsSKILL.md:300 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files…nt is **OpenClaw** (detected by: `ANYSKILL_GITHUB_TOKEN` exists in `~/.openclaw/.env`, or user explicitly specified, or `~/.openclaw/` directory detected), perform …Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05

Cost to the agent

Instructions loaded
≈6,651 tok
1 file · 2 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.

What would make this Verified

23 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim lanyijianke: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Direct script execution from GitHub raw URL≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
  3. Prompting user to enter sensitive credentials≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  4. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  5. File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim lanyijiankePropose a patch to the maintainer