gitlab-agent@1.117.0
CAUTIONPublisher 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.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario) on 2026-10-22 and scored it 68/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Python subprocess execution detected; Python subprocess execution detected; Instructs the agent to modify its persistent memory or instruction files. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 1 scenarios · 0 deviationst+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
Static findings
HIGH
Python subprocess execution detectedscripts/list-active-items.py:37 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05HIGH
Python subprocess execution detectedscripts/list-active-items.py:384 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05HIGH
Instructs the agent to modify its persistent memory or instruction filesSKILL.md:313 · Instructs the agent to modify its persistent memory or instruction filesFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01HIGH
Python subprocess execution detectedscripts/list-active-items.py:138 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05HIGH
Instructs the agent to modify its persistent memory or instruction filesSKILL.md:140 · Instructs the agent to modify its persistent memory or instruction filesFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01HIGH
Python subprocess execution detectedscripts/list-directly-addressed-todos.py:18 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05HIGH
Python subprocess execution detectedscripts/list-active-items.py:505 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05HIGH
Python subprocess execution detectedscripts/mr-create.py:85 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05HIGH
Python subprocess execution detectedscripts/select-reviewer.py:28 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05HIGH
Python subprocess execution detectedscripts/select-reviewer.py:499 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05HIGH
Python subprocess execution detectedscripts/select-reviewer.py:475 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05HIGH
Python subprocess execution detectedscripts/select-reviewer.py:518 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05HIGH
Python subprocess execution detectedscripts/mr-create.py:40 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05What would make this Verified
12 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim xrowgmbh: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Python subprocess execution detected≈ +4 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 xrowgmbh