Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
uStack
v0.1.0Universal agent workspace compatibility and update engine. Track upstream agent frameworks (like gstack), analyze every change, classify portability, and gen...
⭐ 0· 44·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The skill claims to import, diff/analyze, and publish updates from upstream agent repos and the code implements exactly that: git clone/pull, git diff/log, file inspection, IR extraction, and markdown generation. One mismatch: the package/README/SKILL.md document Node.js >=20 and Git as requirements, but the registry metadata lists no required binaries—so the metadata underreports required runtime tools.
Instruction Scope
Runtime instructions and code operate on user-provided Git repository URLs: cloning/pulling repos and reading/writing files under a local .ustack workspace. The tool runs git via child_process and reads many repository files to build reports. It does not request secrets or call external services beyond git network access to the supplied repo URL, nor does it execute arbitrary repo scripts. Because it clones arbitrary repos, run it in an isolated directory/container when importing untrusted repositories.
Install Mechanism
There is no install spec (instruction-only/install-from-source), package.json contains no external dependencies, and files are not fetched from unknown remote archives. The code expects Node.js and Git (package.json engines and SKILL.md), which is a conventional, low-risk setup. No remote install URL or extracted archives were found.
Credentials
No environment variables, credentials, or config paths are required. The code emits metadata that references service auth types (e.g., 'bearer-token') as IR metadata only; it does not ask for or store secrets. Requested environment access is proportional to the declared functionality.
Persistence & Privilege
always is false and the skill operates only within a .ustack directory under the current working directory. It writes manifests, snapshots, and run artifacts there but does not modify other skills or global agent settings. Autonomous invocation is allowed by default (disable-model-invocation: false) but this is the platform default and not combined with other red flags.
Assessment
uStack appears coherent: it clones/pulls Git repos and analyzes their contents, writes artifacts to .ustack/, and generates Markdown pages. Before installing or running: 1) be aware it requires Node >=20 and git (run in an environment with those installed); the registry metadata did not list these—that's an inconsistency. 2) Only import repositories you trust or run ustack in an isolated directory/container, since it will clone arbitrary repos and write files locally. 3) Review the generated .ustack content and manifests before using any adapted output in production. 4) Note there are minor code/quality issues (e.g., a missing fs import in one extractor) — these look like bugs, not malicious behavior. If you need stronger guarantees, run it in a sandboxed environment or inspect the cloned repo contents before further automated processing.src/commands/doctor.js:16
Shell command execution detected (child_process).
src/lib/git.js:12
Shell command execution detected (child_process).
Patterns worth reviewing
These patterns may indicate risky behavior. Check the VirusTotal and OpenClaw results above for context-aware analysis before installing.Like a lobster shell, security has layers — review code before you run it.
latestvk97183y2rbdqyqafr1a5wv784n84e5td
License
MIT-0
Free to use, modify, and redistribute. No attribution required.