Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Exploration Mode Skill
v1.0.0Autonomously executes research, maintenance, security, reflection, knowledge, and optimization tasks during idle time.
⭐ 0· 94·0 current·0 all-time
by@yzh0916
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
medium confidencePurpose & Capability
The name and description ('exploration mode' for autonomous research, maintenance, security review, etc.) are self-consistent with an instruction-only skill that triggers idle-time tasks. However the claimed capabilities (system cleanup, security review, system optimization) imply access to system resources beyond a simple read-only research scope; the skill does not explain what access it needs or why.
Instruction Scope
SKILL.md is high-level and vague. It instructs the agent to 'autonomously perform tasks during idle time' including system cleanup and security review but provides no concrete boundaries, allowed commands, file paths, or external endpoints. That open-ended autonomy could lead to reading or modifying local files, running commands, or contacting external services — none of which are constrained or justified by the document.
Install Mechanism
Instruction-only skill with no install spec and no code files => low install risk. Nothing is written to disk by an installer and there are no external download URLs to evaluate.
Credentials
The skill requests no environment variables, credentials, or config paths, which is proportionate on paper. However, because instructions are ambiguous about what the agent may access, the absence of declared required secrets does not guarantee the agent won't attempt to read sensitive data at runtime.
Persistence & Privilege
always is false (good). The skill relies on the platform's normal autonomous invocation capability (disable-model-invocation is false), which means the agent can run it during idle time. Autonomous invocation by itself is not flagged, but combined with the skill's vague scope and potentially sensitive task categories (system cleanup/security review), it raises concern about unsupervised activity.
What to consider before installing
This skill is vague about what 'exploration' entails and gives the agent broad, unspecific permission to do system cleanup, security review, and optimizations during idle time. Before installing: 1) Demand a precise, written policy of allowed actions (which directories are in-scope/out-of-scope, whether it may run shell commands, whether it may modify or delete files). 2) Require explicit user confirmation for any destructive or network-capable actions. 3) Prefer a version that limits operations to read-only analysis unless the user opts in to write/delete operations. 4) Ask for logging/audit hooks and a way to revoke or pause the skill. 5) If you cannot get specifics, avoid enabling autonomous invocation or do not install the skill — leave it as user-invoked only and test in a sandbox. Additional information that would raise confidence to 'benign': a detailed SKILL.md enumerating permitted commands, file path restrictions, network endpoints (if any), and explicit safeguards (confirmation prompts, dry-run modes, and logging).Like a lobster shell, security has layers — review code before you run it.
latestvk976et5b2aqd4rnevz3e35yg6d8359hm
License
MIT-0
Free to use, modify, and redistribute. No attribution required.