Skills/ClawHub/xrowgmbh-gitlab-agent

xrowgmbh-gitlab-agent@1.147.5

VERIFIED· install only

Publisher claims: "Operate assigned GitLab work with owner-verified project access and guarded MR delivery." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher xrowgmbh · publishing for 29 daysInstalls 8,156Last detonated 12 h ago
$clawhub install xrowgmbh-gitlab-agent
WatchReport an issue

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
6 of 6 bundled scripts run with no arguments, 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

What changed since 1.146.0

vet-skills diff xrowgmbh-gitlab-agent 1.146.0 1.147.5

In the sandbox, this version reached for nothing 1.146.0 did not. Compared from the two recorded runs, not from source.

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

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 82/100 (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
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments
0.2sprocessexited 2: benchmark-discovery.py: error: the following arguments are required: --baseline
0.2sprocessbundled script run in the sandbox with no arguments
0.2sprocessexited 69:
0.2sprocessbundled script run in the sandbox with no arguments
0.2sfilesystemread ~/.openclaw/openclaw.json outside project
0.2sprocessexited 1: Unable to list owner-addressed GitLab to-dos: [Errno 2] No such file or directory: '/tmp/ks-detonate-pALlkj/scripts/home/.openclaw/openclaw.json'
0.2sprocessbundled script run in the sandbox with no arguments
0.3sprocessexited 2: select-reviewer.py: error: the following arguments are required: project_path, mr_iid
0.3sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.4sfilesystemread ~/.openclaw/openclaw.json outside project
0.4sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.5sprocessexec /app/apps/web/node_modules/.bin/glab
0.5sprocessexec /root/.cache/node/corepack/v1/pnpm/10.28.0/dist/node-gyp-bin/glab
0.5sprocessexec /app/node_modules/.bin/glab
0.5sprocessexec /pnpm/glab
0.5sprocessexec /usr/local/sbin/glab
0.5sprocessexec /usr/local/bin/glab
0.5sprocessexec /usr/sbin/glab
0.5sprocessexec /usr/bin/glab
0.5sprocessexec /sbin/glab
0.5sprocessexec /bin/glab
0.5sprocessexited 1: WORK_QUEUE_ERROR={"error_code": "helper-permission"}
0.5sprocess6 of 6 bundled scripts run with no arguments
0.5sprocessscript backend runs setup only
0.5sprocessscript backend runs setup only
0.5sprocessno install scripts to re-run

Static findings

MEDIUM
Python subprocess execution detectedscripts/list-active-items.py:498 · Python subprocess execution detectedwrite = subprocess.run(command, check=True, text=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/list-active-items.py:70 · Python subprocess execution detectedreturn subprocess.run(command, timeout=25, **kwargs)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/select-reviewer.py:28 · 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 detectedscripts/list-active-items.py:630 · Python subprocess execution detectedresult = subprocess.run(command, check=True, text=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/test_discovery_runtime.py:80 · Python subprocess execution detectedsubprocess.run([sys.executable, "-S", "-c", program, str(SCRIPT)], check=True, capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/test_work_queue_problems.py:92 · Python subprocess execution detectedresult = subprocess.run(['python3', str(DIRECTORY / name)], 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
MEDIUM
Python subprocess execution detectedscripts/list-active-items.py:76 · Python subprocess execution detectedreturn subprocess.run(command, timeout=25, **kwargs)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/list-directly-addressed-todos.py:21 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Instructs the agent to modify its persistent memory or instruction filesSKILL.md:301 · Instructs the agent to modify its persistent memory or instruction files* Only modify the `AGENTS.md` file, if requested by a maintainer.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Python subprocess execution detectedscripts/select-reviewer.py:703 · 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 detectedscripts/list-active-items.py:223 · Python subprocess execution detectedsubprocess.run(command, check=True, stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedscripts/select-reviewer.py:680 · 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 detectedscripts/select-reviewer.py:723 · Python subprocess execution detectedmerged = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
Dynamic module loadingscripts/benchmark-discovery.py:28 · Dynamic module loadingmodule = importlib.util.module_from_spec(spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Python subprocess execution detectedscripts/work-queue-report.py:33 · Python subprocess execution detectedresult = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
Dynamic module loadingscripts/test_owner_config.py:22 · Dynamic module loading (importlib.loader.exec_module via provenance)spec.loader.exec_module(module)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Dynamic module loadingscripts/test_work_queue_report.py:13 · Dynamic module loadingqueue = importlib.util.module_from_spec(spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Dynamic module loadingscripts/test_discovery_runtime.py:75 · Dynamic module loading (importlib.loader.exec_module via provenance)spec.loader.exec_module(active)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Dynamic module loadingscripts/test_list_active_items.py:20 · Dynamic module loading (importlib.loader.exec_module via provenance)spec.loader.exec_module(active)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Dynamic module loadingscripts/test_list_active_items_incidents.py:16 · Dynamic module loadingmodule = importlib.util.module_from_spec(SPEC)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Dynamic module loadingscripts/test_select_reviewer.py:22 · Dynamic module loading (importlib.loader.exec_module via provenance)SPEC.loader.exec_module(reviewer)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Dynamic module loadingscripts/test_work_queue_report.py:14 · Dynamic module loading (importlib.loader.exec_module via provenance)spec.loader.exec_module(queue)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Dynamic module loadingscripts/test_discovery_runtime.py:22 · Dynamic module loading (importlib.loader.exec_module via provenance)spec.loader.exec_module(module)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Dynamic module loadingscripts/test_list_active_items_collaborators.py:23 · Dynamic module loadingactive = importlib.util.module_from_spec(spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Dynamic module loadingscripts/test_owner_config.py:21 · Dynamic module loadingmodule = importlib.util.module_from_spec(spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Dynamic module loadingscripts/test_discovery_performance.py:17 · Dynamic module loadingbench = importlib.util.module_from_spec(SPEC)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Dynamic module loadingscripts/test_discovery_runtime.py:21 · Dynamic module loadingmodule = importlib.util.module_from_spec(spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Dynamic module loadingscripts/test_discovery_read_timeouts.py:18 · Dynamic module loadingmodule = importlib.util.module_from_spec(spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Dynamic module loadingscripts/test_discovery_read_timeouts.py:19 · Dynamic module loading (importlib.loader.exec_module via provenance)spec.loader.exec_module(module)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Dynamic module loadingscripts/benchmark-discovery.py:29 · Dynamic module loading (importlib.loader.exec_module via provenance)spec.loader.exec_module(module)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Dynamic module loadingscripts/test_discovery_graphql.py:30 · Dynamic module loadingself.active = importlib.util.module_from_spec(spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Dynamic module loadingscripts/work-queue-problems.py:16 · Dynamic module loadingqueue = importlib.util.module_from_spec(spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Dynamic module loadingscripts/test_discovery_graphql.py:31 · Dynamic module loading (importlib.loader.exec_module via provenance)spec.loader.exec_module(self.active)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Dynamic module loadingscripts/test_select_reviewer.py:21 · Dynamic module loadingreviewer = importlib.util.module_from_spec(SPEC)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Dynamic module loadingscripts/work-queue-report.py:24 · Dynamic module loading (importlib.loader.exec_module via provenance)spec.loader.exec_module(module)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Dynamic module loadingscripts/test_list_active_items_incidents.py:17 · Dynamic module loading (importlib.loader.exec_module via provenance)SPEC.loader.exec_module(module)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Dynamic module loadingscripts/test_list_directly_addressed_todos.py:18 · Dynamic module loadingtodos = importlib.util.module_from_spec(spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Dynamic module loadingscripts/test_work_queue_problems.py:19 · Dynamic module loading (importlib.loader.exec_module via provenance)spec.loader.exec_module(module)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Dynamic module loadingscripts/test_discovery_performance.py:18 · Dynamic module loading (importlib.loader.exec_module via provenance)SPEC.loader.exec_module(bench)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Dynamic module loadingscripts/test_discovery_runtime.py:74 · Dynamic module loadingactive = importlib.util.module_from_spec(spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Dynamic module loadingscripts/test_list_directly_addressed_todos.py:19 · Dynamic module loading (importlib.loader.exec_module via provenance)spec.loader.exec_module(todos)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Dynamic module loadingscripts/test_list_active_items_collaborators.py:24 · Dynamic module loading (importlib.loader.exec_module via provenance)spec.loader.exec_module(active)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Dynamic module loadingscripts/test_list_active_items.py:19 · Dynamic module loadingactive = importlib.util.module_from_spec(spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Dynamic module loadingscripts/work-queue-report.py:23 · Dynamic module loadingmodule = importlib.util.module_from_spec(spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Dynamic module loadingscripts/work-queue-problems.py:17 · Dynamic module loading (importlib.loader.exec_module via provenance)spec.loader.exec_module(queue)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Dynamic module loadingscripts/test_work_queue_problems.py:18 · Dynamic module loadingmodule = importlib.util.module_from_spec(spec)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈5,618 tok
1 file · 24 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.