Skill flagged — suspicious patterns detected

ClawHub Security flagged this skill as suspicious. Review the scan results before using.

Productivity Helper #3

v1.0.0

Productivity helper tool #3 for task management, time tracking, and workflow optimization. Helps organize daily tasks and boost efficiency.

0· 1·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Suspicious
medium confidence
Purpose & Capability
The name and description claim a simple productivity/task helper. The SKILL.md is an instruction-only file that provides only high-level user prompts (planning tasks, time tracking). However, README.md contains manual-install instructions (git clone https://github.com/TobeyRebecca/productivity-helper.git and clawhub install toby-productivity-helper) which implies there may be a separate code repo or packaged code — but no code files or install spec are included in the skill bundle. This mismatch (README implying a code package while the uploaded skill is instruction-only) is unexpected and should be clarified.
!
Instruction Scope
SKILL.md itself contains only high-level instructions and does not tell the agent to read user files, env vars, or contact external endpoints. However the skill metadata header permits use of 'Bash' and 'Read'/'Write' tools. Those permissions allow the agent to run arbitrary shell commands and read/write local files despite the instructions never justifying that capability. The SKILL.md also contains an external link to a 'Complete setup guide' (https://skillboss.co/skill.md) which could direct the agent or user to follow further instructions outside the packaged skill.
Install Mechanism
There is no install spec in the skill bundle (instruction-only), so nothing is written to disk by an installer. That is low risk. The README suggests manual installation via git clone from a GitHub repo and a clawhub install command; because no install spec is included in the skill bundle, those README instructions are either stale/templates or refer to an external project — this is a mismatch but not an active install risk in the current package.
!
Credentials
The skill declares no required environment variables or config paths (which is appropriate for a simple task helper). But the allowed-tools header grants Bash and file Read/Write access without any justification in the instructions. Granting shell access is disproportionate to the stated purpose of organizing tasks unless the skill explicitly needs to read/write local task files; that need is not documented. This increases the potential for local file access or accidental data exposure.
Persistence & Privilege
The skill does not request persistent privileges (always: false) and is user-invocable only. It does not declare modifications to other skills or system-wide settings. Autonomous invocation remains enabled by default but is not in itself a distinguishing risk here.
What to consider before installing
This skill appears to be a simple instruction-only productivity helper, but there are a few inconsistencies you should consider before installing or enabling it: - The SKILL.md allows Bash and file Read/Write tools even though the instructions don't justify needing shell access. Allowing Bash gives the skill the ability to run arbitrary local commands and access files — if you don't trust the skill, remove or restrict the Bash permission. - README.md references a GitHub repo and install commands (git clone, clawhub install) despite the uploaded bundle containing no code or install spec. That could mean the published skill is a lightweight wrapper for code hosted elsewhere — check the referenced repository and verify its contents and origin before following any install steps. - The SKILL.md includes an external link to a 'Complete setup guide' (skillboss.co). External links can lead to further installation or credential-request steps not visible in this package; inspect those pages and their domains before providing any credentials or running commands. Recommended actions: - Ask the publisher for clarification: Do they intend this skill to be instruction-only or to pull code from the GitHub repo? If the latter, request the exact repo URL and verify the code before allowing installation. - If you want to use it, run it with restricted permissions first (disable Bash, limit Read/Write to a dedicated sandbox folder) and monitor what the skill reads or writes. - Avoid granting any secrets or broad OS-level permissions. If you are not comfortable reviewing an external repo or these permissions, do not install. Confidence: medium — the package is not obviously malicious, but the mismatches and overly-broad allowed-tools justify caution and further verification.

Like a lobster shell, security has layers — review code before you run it.

automationvk975q45t36t0msehg7sw313yzh84rtavlatestvk975q45t36t0msehg7sw313yzh84rtavproductivityvk975q45t36t0msehg7sw313yzh84rtavtasksvk975q45t36t0msehg7sw313yzh84rtavworkflowvk975q45t36t0msehg7sw313yzh84rtav

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

Runtime requirements

Clawdis

Comments