Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
IELTS Tutor
v1.0.0IELTS exam tutoring skill using a structured "quiz → attempt → correction → review" loop. This skill should be used when the user wants to practice IELTS wri...
⭐ 0· 49·0 current·0 all-time
byChang Liu@liuchang0812
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
Capability signals
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
OpenClaw
Suspicious
high confidencePurpose & Capability
Name, description, and instructions align: the skill generates exercises, accepts answers, corrects them, and summarizes progress. The included references/learner-profile.md is appropriate for tailoring exercises.
Instruction Scope
SKILL.md explicitly instructs the agent to 'Load references/learner-profile.md' (included) and also to 'check memory/MEMORY.md for the most up-to-date progress tracking.' The skill metadata did not declare any required config paths; referencing memory/MEMORY.md is a cross-boundary read of agent state that isn't declared and may expose unrelated user data. No instructions call external endpoints, but the undeclared memory file access is scope creep.
Install Mechanism
Instruction-only skill with no install spec and no code files; nothing is written to disk or downloaded by an installer. This is the lowest-risk install model.
Credentials
No environment variables, credentials, or binaries are requested—appropriate for this purpose. However, the instruction to read memory/MEMORY.md implies access to persistent agent data (not declared), which could include personal or historical information; that access should be justified or declared.
Persistence & Privilege
The skill is not set to always:true and does not request to modify other skills or system settings. It can be invoked autonomously (platform default). Autonomous invocation combined with undeclared access to agent memory increases the potential blast radius, but autonomous invocation alone is normal.
What to consider before installing
This skill appears to be a legitimate IELTS tutor and is instruction-only (no installers or external network calls). The main issue: SKILL.md tells the agent to check memory/MEMORY.md for up-to-date progress, but the skill metadata does not declare that path. That means the skill could read your agent's stored memory or past interactions without that being listed as a required config path. Before installing or enabling the skill: 1) Inspect your agent's MEMORY.md (or equivalent) to see what it contains; avoid exposing sensitive personal data there. 2) If you don't want the skill to access past conversations or personal info, either remove/empty MEMORY.md or deny the skill access in your agent settings. 3) Consider testing the skill with dummy profile/memory data first. 4) If you are concerned about autonomous invocation, disable autonomous invocation for this skill or require explicit user prompts. If the maintainer can justify and declare the memory path in the metadata (or remove the memory reference from SKILL.md), this concern would be resolved.Like a lobster shell, security has layers — review code before you run it.
latestvk973ss7p6e2dxe83snaxj8ngq184pvw6
License
MIT-0
Free to use, modify, and redistribute. No attribution required.