Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
long-context-shell
v0.0.1Runs long or continuous shell commands with file-backed logs, truncated previews, and fast log scanning. Invoke when shell output may be large, ongoing, or h...
⭐ 1· 94·0 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's name and description (long-running shell commands with file-backed logs and scanning) match the provided code and SKILL.md. The handler spawns shell processes, timestamps stdout/stderr into log files, tracks sessions, provides peek/scan/stop tools, and includes tests exercising those features — all expected for this purpose.
Instruction Scope
SKILL.md and the code both instruct the agent to execute arbitrary shell commands via the platform shell and to persist logs and session state under a tmp directory. This is expected for a shell-monitoring tool, but it inherently grants the skill the ability to execute any command the user supplies. The README includes safety guidance (ask before destructive commands), but the code does not enforce a separate approval step — enforcement is left to the agent/owner. Users should be aware that if the agent is instructed (or allowed) to run destructive or privilege-escalating commands, those commands will run with the agent's OS user privileges.
Install Mechanism
There is no install spec (instruction-only skill with bundled code). No external downloads or package installs are required. The code runs from the skill bundle and writes to a temp directory, which is a low-risk install pattern.
Credentials
The skill does not request environment variables, credentials, or config paths. The code only writes/reads session and log files under os.tmpdir() and uses standard Node APIs. No external service credentials are requested or used.
Persistence & Privilege
The skill persists session JSON and log files under a dedicated tmp directory (os.tmpdir()/trae-long-context-shell). It is not marked always:true. Autonomous invocation is allowed (default), which is normal for skills; combined with the ability to execute arbitrary shell commands, that means an agent with this skill could run commands without an extra install-time prompt if the agent is authorized to do so. There is no evidence the skill modifies other skills or system configurations.
Assessment
This skill appears coherent and implements what it promises: executing user-provided shell commands, writing timestamped logs to a temp folder, offering truncated previews, scanning for common error patterns, and stopping background sessions. Before installing or invoking it, consider: (1) it will execute any command you pass (shell -lc on Unix or PowerShell on Windows) — avoid sending destructive or privileged commands unless you explicitly approve them; (2) it stores logs and session state under your system temp directory (trae-long-context-shell) — remove stale sessions/logs if needed; (3) no credentials are requested, but the skill runs with the agent process's OS privileges, so ensure the agent runs in an appropriate sandbox; (4) if you need stricter safeguards, review the handler.js code locally or run the included tests in a safe environment to confirm behavior. Overall the skill is internally consistent, but exercise the usual caution because it executes arbitrary shell commands.handler.js:169
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.
latestvk97cvpebsqq1g4hd25t7ssb3ss83g2k8
License
MIT-0
Free to use, modify, and redistribute. No attribution required.