Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Decision Mode
v1.0.0Activate when the user asks a question that requires judgment, choice, or decision-making. This skill helps provide structured decision support by analyzing...
⭐ 0· 154·0 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 match the instructions: a decision-support framework that recommends searching for time‑sensitive information, cites sources, and weighs perspectives. No binaries, credentials, or installs are requested, which is appropriate for an instruction-only decision aid.
Instruction Scope
The runtime instructions are detailed and scoped to decision analysis (information gathering, dual perspectives, confidence scoring). However there is an internal contradiction: an earlier rule allows proceeding without search for 'general principle' questions, while 'Step 0' emphatically states 'BEFORE providing any analysis, you MUST gather current information.' This ambiguity could cause the agent to perform searches for queries where they aren't needed. The spec also instructs agents to use web_search/web_fetch/browser and to incorporate conversation history — which is expected but could increase external requests and privacy exposure if left unconstrained.
Install Mechanism
No install steps, no code files, and no downloads — lowest-risk deployment model. The skill is instruction-only and does not write to disk or execute installed binaries.
Credentials
No environment variables, credentials, or config paths are requested. The skill's needs are proportional to its stated purpose.
Persistence & Privilege
The skill is not always-enabled and is user-invocable. It does not request elevated persistence or modify other skills. Autonomous invocation remains possible (platform default) but is not flagged here by itself.
What to consider before installing
This skill appears to be what it says: a structured decision-making framework. Before installing, consider: (1) Clarify the search rule — do you want the agent to 'always' perform external searches or only for time‑sensitive queries? The SKILL.md currently contradicts itself and could cause unnecessary web lookups. (2) If you care about privacy, confirm how the agent's browser/search connectors handle user data and whether queries derived from private context will be sent to external services. (3) Because the skill instructs the agent to include conversation history and cite external sources, test it in a safe sandbox to see how often it performs web_fetch/browser calls and what it sends. If you want stricter behavior, ask the author to remove the absolute 'MUST gather current information' or to provide clear rules for when searches are required.Like a lobster shell, security has layers — review code before you run it.
analysisvk978rcfmfntsjwexzsm2m68mb582y1zvconfidencevk978rcfmfntsjwexzsm2m68mb582y1zvdecisionvk978rcfmfntsjwexzsm2m68mb582y1zvlatestvk978rcfmfntsjwexzsm2m68mb582y1zv
License
MIT-0
Free to use, modify, and redistribute. No attribution required.