Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Worker Executor
v1.0.0Performs specific tasks like research, writing, coding, or analysis with concrete, fast execution while staying strictly within assigned scope.
⭐ 0· 243·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
medium confidencePurpose & Capability
Name and description ('worker/executor' for research, writing, coding, analysis) match the SKILL.md instructions. The skill requests no binaries, no environment variables, and no installs — this is proportionate to an instruction-only executor role.
Instruction Scope
SKILL.md defines a clear worker role and response protocol, but the core directive to 'Execute it thoroughly' is high-level and does not constrain what system actions are allowed (file I/O, networking, running tools). The instructions do not reference any specific files, paths, or external endpoints, but they also do not explicitly forbid accessing them. This vagueness grants the agent broad discretion at runtime and could result in actions outside what a user expects unless the agent runtime enforces policy limits.
Install Mechanism
No install spec and no code files — lowest-risk delivery mechanism (instruction-only). Nothing will be downloaded or written to disk by the skill package itself.
Credentials
The skill does not request any environment variables, credentials, or config paths. There are no disproportionate credential requests.
Persistence & Privilege
always is false and there is no install activity. The skill can be invoked autonomously by an agent (default platform behavior). Combined with the skill's broad execution instructions, autonomous invocation increases potential blast radius depending on what tools/permissions the agent has, but on its own this is normal behavior.
What to consider before installing
This skill is an instruction-only 'doer' role that tells an agent to execute tasks and return results. On its face it's coherent, but its instructions are intentionally broad and do not limit what system actions are permitted. Before installing or enabling it, consider:
- What runtime tools and permissions will the agent have? (file system, network, shell access, cloud credentials)
- If you don't want the agent to perform I/O or network calls, ensure the runtime enforces those restrictions or update SKILL.md to explicitly forbid them.
- Prefer running this skill only with agents or environments that have minimal privileges and clear audit/logging so you can review actions taken.
- Ask the publisher to add explicit boundaries (allowed/disallowed operations), examples of permitted tasks, and safe-usage recommendations.
If you can confirm the agent runtime will restrict filesystem/network/credential access appropriately, this skill becomes much lower risk. Without that assurance, the broad 'execute' directive is the reason for the caution.Like a lobster shell, security has layers — review code before you run it.
latestvk971jqa3f1xc3evjsra616g80h82qs2f
License
MIT-0
Free to use, modify, and redistribute. No attribution required.