Skills/ClawHub/clawguard-scanner

clawguard-scanner@0.1.0

CAUTION· static only

Publisher claims: "Security scanner for OpenClaw skills. Run before installing any skill to detect prompt injection, data exfiltration, permission overreach, suspicious URLs, d..." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher frrrrrrrrank · publishing for 249 daysInstalls 1,248Last detonated 26 min 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 2026-11-20 and scored it 51/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Reads credential paths from the home directory; Pipe-to-shell pattern; Access to sensitive file paths. 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
Reads credential paths from the home directorySKILL.md:47 · Reads credential paths from the home directory| CRITICAL | `data-exfiltration` — reading sensitive files (~/.ssh, ~/.aws) and sending externally |Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
HIGH
Pipe-to-shell patternSKILL.md:50 · Pipe-to-shell pattern — downloads and immediately executes remote code| HIGH | `dangerous-commands` — rm -rf /, curl \| sh, system file modification |Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
MEDIUM
npx invocation of non-well-known packageSKILL.md:37 · npx invocation of non-well-known package — may execute untrusted codenpx clawguard scan <path-to-skill-directory> --rules prompt-injection,data-exfiltrationFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageSKILL.md:31 · npx invocation of non-well-known package — may execute untrusted codenpx clawguard scan <path-to-skill-directory> --jsonFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathsSKILL.md:47 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files| CRITICAL | `data-exfiltration` — reading sensitive files (~/.ssh, ~/.aws) and sending externally |Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Remote installer piped to shellSKILL.md:50 · Remote installer piped to shell| HIGH | `dangerous-commands` — rm -rf /, curl \| sh, system file modification |Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
HIGH
Destructive file system command detectedSKILL.md:50 · Destructive file system command detected| HIGH | `dangerous-commands` — rm -rf /, curl \| sh, system file modification |Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
npx invocation of non-well-known packageSKILL.md:25 · npx invocation of non-well-known package — may execute untrusted codenpx clawguard scan <path-to-skill-directory>Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageSKILL.md:73 · npx invocation of non-well-known package — may execute untrusted code2. Run `npx clawguard scan <skill-dir>`Fix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈837 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

29 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim frrrrrrrrank: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Reads credential paths from the home directory≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  3. Pipe-to-shell pattern≈ +4 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  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. Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  6. npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim frrrrrrrrankPropose a patch to the maintainer