Skills/ClawHub/skills-coach

skills-coach@2.3.1

CAUTION· install only

Publisher claims: "Explore capability boundaries of a target Skill, analyze optimization potential, generate an optimized version using Training-Free GRPO, and compile results..." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher t1ans1r · publishing for 205 daysInstalls 771Last detonated 14 h ago

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
8 of 22 bundled scripts run with no arguments (the rest were not run: per-bundle cap), with decoy credentials in the environment · 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; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-19 and scored it 70/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Pipe-to-shell pattern; Destructive file system command detected; Pipe-to-shell pattern. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 1 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.1sprocessexited 1: EOFError: EOF when reading a line
0.1sprocessbundled script run in the sandbox with no arguments
0.1sprocessexited 1: ModuleNotFoundError: No module named 'yaml'
0.1sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.1sprocessexited 1: ModuleNotFoundError: No module named 'psutil'
0.1sprocessbundled script run in the sandbox with no arguments
0.3sprocessexec /usr/bin/cat
0.3sprocessexec /usr/bin/wc
0.3sprocessexec /usr/bin/awk
0.3sprocessexec /usr/bin/grep
0.3sprocessbundled script run in the sandbox with no arguments
0.3sprocessexited 1: ModuleNotFoundError: No module named 'yaml'
0.3sprocessbundled script run in the sandbox with no arguments
0.3sprocessexited 1: ModuleNotFoundError: No module named 'yaml'
0.3sprocessbundled script run in the sandbox with no arguments
0.4sprocessexited 1: ModuleNotFoundError: No module named 'yaml'
0.4sprocessbundled script run in the sandbox with no arguments
0.4sprocessexited 1: ModuleNotFoundError: No module named 'yaml'
0.4sprocess8 of 22 bundled scripts run with no arguments (the rest were not run: per-bundle cap)
0.4sprocessscript backend runs setup only
0.4sprocessscript backend runs setup only
0.4sprocessno install scripts to re-run

Static findings

CRITICAL
Pipe-to-shell patternsubskills/exec-agent/env_checker.py:170 · Pipe-to-shell pattern — downloads and immediately executes remote code'cargo': 'curl --proto \'=https\' --tlsv1.2 -sSf https://sh.rustup.rs | sh',Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
HIGH
Destructive file system command detectedsubskills/exec-agent/SKILL.md:121 · Destructive file system command detectedrm -rf /tmp/exec_original_task_XXXFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedsubskills/evaluate-agent/evaluator.py:190 · Python subprocess execution detectedresult = subprocess.run(Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
MEDIUM
Python subprocess execution detectedorchestrator.py:442 · Python subprocess execution detectedresult = subprocess.run(cmd, capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
CRITICAL
Pipe-to-shell patternsubskills/exec-agent/env_checker.py:180 · Pipe-to-shell pattern — downloads and immediately executes remote code'uv': 'Install with: brew install uv OR curl -LsSf https://astral.sh/uv/install.sh | sh',Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
MEDIUM
Python subprocess execution detectedorchestrator.py:186 · Python subprocess execution detectedresult = subprocess.run(cmd, cwd=sample_agent_dir)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
CRITICAL
Pipe-to-shell patternsubskills/exec-agent/env_checker.py:187 · Pipe-to-shell pattern — downloads and immediately executes remote code'cargo': 'Install with: curl --proto \'=https\' --tlsv1.2 -sSf https://sh.rustup.rs | sh',Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
HIGH
Agent configured for autonomous execution without human approvalSKILL.md:421 · Agent configured for autonomous execution without human approval- All subskills operate autonomously without user input between stepsFix: Declare and request only the permissions the task needs.
AST02
MEDIUM
Python subprocess execution detectedorchestrator.py:154 · Python subprocess execution detectedresult = subprocess.run(cmd, cwd=detector_dir)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedorchestrator.py:478 · Python subprocess execution detectedresult = subprocess.run(cmd, cwd=evaluate_agent_dir)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsubskills/exec-agent/env_checker.py:80 · 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
Python subprocess execution detectedorchestrator.py:371 · Python subprocess execution detectedresult = subprocess.run(cmd, capture_output=True, text=True) # Don't change cwdFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedarchive/backups/training_free_grpo_simple.py:34 · Python subprocess execution detectedresult = subprocess.run(cmd, cwd=optimize_agent_dir)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedorchestrator.py:322 · Python subprocess execution detectedresult = subprocess.run(cmd, cwd=exec_agent_dir)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedorchestrator.py:242 · Python subprocess execution detectedprocess = subprocess.Popen(cmd, cwd=optimize_agent_dir)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedsubskills/exec-agent/env_checker.py:211 · 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
Python subprocess execution detectedsubskills/exec-agent/executor.py:151 · 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 shellsubskills/exec-agent/env_checker.py:180 · Remote installer piped to shell'uv': 'Install with: brew install uv OR curl -LsSf https://astral.sh/uv/install.sh | sh',Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
Remote installer piped to shellsubskills/exec-agent/env_checker.py:170 · Remote installer piped to shell'cargo': 'curl --proto \'=https\' --tlsv1.2 -sSf https://sh.rustup.rs | sh',Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
Python subprocess execution detectedsubskills/optimize-agent/command_optimizer.py:125 · 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
Process kill commandorchestrator.py:251 · Process kill command — agent can terminate processes"""Monitor the process and kill if stuck."""Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedsubskills/optimize-agent/training_free_grpo_optimizer.py:862 · 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
Python subprocess execution detectedsubskills/exec-agent/env_checker.py:111 · 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
Process kill commandprocess_monitor.py:91 · Process kill command — agent can terminate processesreturn False, f"Failed to kill stuck process: {e}"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commandprocess_monitor.py:15 · Process kill command — agent can terminate processes"""Monitor a subprocess and kill it if stuck."""Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedsubskills/optimize-agent/grpo_optimizer.py:421 · 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 shellsubskills/exec-agent/env_checker.py:187 · Remote installer piped to shell'cargo': 'Install with: curl --proto \'=https\' --tlsv1.2 -sSf https://sh.rustup.rs | sh',Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07

Cost to the agent

Instructions loaded
≈9,040 tok
5 files · 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

10 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Pipe-to-shell pattern≈ +9 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  2. Unclaimed publisher≈ +8 on the totalClaim t1ans1r: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  4. Agent configured for autonomous execution without human approval≈ +4 on the totalDeclare and request only the permissions the task needs.
  5. Python subprocess execution detected≈ +2 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
  6. Remote installer piped to shell≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim t1ans1rPropose a patch to the maintainer