Skills/ClawHub/openclaw-skill-eval

openclaw-skill-eval@1.1.1

VERIFIED· install only

Publisher claims: "Skill evaluation framework. Use when: testing trigger rate, quality compare (with/without skill), or model comparison. Runs via sessions_spawn + sessions_his..." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher xiaoxing9 · publishing for 246 daysInstalls 1,200Last detonated 15 min ago
$clawhub install openclaw-skill-eval
WatchReport an issue

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
8 of 15 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 2026-11-20 and scored it 85/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. 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
0.1sprocessexited 2: aggregate_benchmark.py: error: the following arguments are required: benchmark_dir
0.1sprocessbundled script run in the sandbox with no arguments
0.1sprocessexited 2: analyze_latency.py: error: the following arguments are required: --evals, --timings-dir, --output-dir
0.1sprocessbundled script run in the sandbox with no arguments
0.2sprocessexited 2: analyze_model_compare.py: error: the following arguments are required: --evals, --data-dir, --models, --output-dir
0.2sprocessbundled script run in the sandbox with no arguments
0.3sprocessexited 2: analyze_quality.py: error: the following arguments are required: --evals, --transcripts, --output
0.3sprocessbundled script run in the sandbox with no arguments
0.4sprocessexited 2: analyze_triggers.py: error: the following arguments are required: --evals, --histories, --output
0.4sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.5sprocessexited 2: build_evals_with_context.py: error: the following arguments are required: --base-evals
0.5sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.6sprocessexited 1: ModuleNotFoundError: No module named 'oc_tools'
0.6sprocessbundled script run in the sandbox with no arguments
0.7sprocessexited 2: resolve_paths.py: error: the following arguments are required: skill_name
0.7sprocess8 of 15 bundled scripts run with no arguments (the rest were not run: per-bundle cap)
0.7sprocessscript backend runs setup only
0.7sprocessscript backend runs setup only
0.7sprocessno install scripts to re-run

Static findings

MEDIUM
Python exec or eval of computed codescripts/analyze_triggers.py:243 · Python exec or eval of computed codehelp="Show detailed output per eval (default: summary only)"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 exec or eval of computed codescripts/analyze_quality.py:210 · Python exec or eval of computed codehelp="Show detailed output per eval (default: summary only)"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 exec or eval of computed codescripts/analyze_model_compare.py:330 · Python exec or eval of computed codehelp="Show detailed output per eval (default: summary only)"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 exec or eval of computed codescripts/legacy/run_diagnostics.py:605 · Python exec or eval of computed codehelp="Show detailed output per eval (default: summary only)"Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
MEDIUM
File type combined with upload actionSKILL.md:182 · File type combined with upload action — agent may exfiltrate local data files├── trigger_results.json ← analyze_triggers outputFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Python exec or eval of computed codescripts/build_evals_with_context.py:89 · Python exec or eval of computed code- "parallel": create two versions per eval (fresh + with-context)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 detectedscripts/legacy/run_orchestrator.py:158 · Python subprocess execution detectedresult = subprocess.run(cmd, cwd=Path(__file__).parent)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python exec or eval of computed codescripts/legacy/run_compare.py:91 · Python exec or eval of computed code"""Process a single eval (fetch histories, extract transcripts, save files).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 exec or eval of computed codescripts/analyze_latency.py:219 · Python exec or eval of computed codehelp="Show detailed output per eval (default: summary only)"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 detectedscripts/legacy/run_orchestrator.py:227 · Python subprocess execution detectedresult = subprocess.run(cmd, cwd=Path(__file__).parent)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actionSKILL.md:183 · File type combined with upload action — agent may exfiltrate local data files├── quality_results.json ← analyze_quality outputFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Python subprocess execution detectedviewer/generate_review.py:291 · 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 exec or eval of computed codescripts/legacy/run_latency_profile.py:495 · Python exec or eval of computed codehelp="Number of runs per eval (min 3 for meaningful stats). Default: 5"Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
MEDIUM
Process kill commandviewer/generate_review.py:445 · Process kill command — agent can terminate processes# Port still in use after kill attempt — find a free oneFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈2,519 tok
2 files · 41 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.

openclaw-skill-eval@1.1.1 safety verdict: Verified (install only) — KillerSkills