Back to skill
Skillv2.0.0

ClawScan security

DeFi · ClawHub's context-aware review of the artifact, metadata, and declared behavior.

Scanner verdict

BenignMar 11, 2026, 10:14 AM
Verdict
benign
Confidence
high
Model
gpt-5-mini
Summary
The skill's stated purpose (DeFi protocol risk analysis and yield realism) matches its instructions and requirements: it's instruction-only, asks for no credentials, performs advisory analysis, and contains no install or runtime code that contradicts its description.
Guidance
This skill appears internally consistent and advisory-only. Before using it: (1) never paste seed phrases, private keys, or other secrets into the chat; only paste transaction logs or public addresses if you consent; (2) verify the host platform's privacy policy for any pasted data (transaction logs can include identifying info); (3) if the skill asks for credentials or to run code, stop and refuse—those would contradict its stated boundaries; (4) if you want extra assurance, check the referenced GitHub homepage (skill.json lists one) to inspect source history and issues before relying on its judgments.

Review Dimensions

Purpose & Capability
okName, description, and declared capabilities align with the SKILL.md and skill.json. The skill is advisory-only and does not request keys, RPC credentials, or binaries that would be unnecessary for analysis.
Instruction Scope
noteInstructions stay within an analysis-only scope and explicitly forbid wallet/key handling. The skill may ask users to paste transaction logs or protocol metadata for analysis — that is expected but users should avoid pasting private keys or other secrets. No steps instruct the agent to read unrelated system files or to send data to unexpected external endpoints.
Install Mechanism
okNo install spec and no code files; this is instruction-only so nothing is written to disk or downloaded during install.
Credentials
okThe skill declares no required environment variables, credentials, or config paths. There are no extraneous credential requests that would be disproportionate to a DeFi analysis tool.
Persistence & Privilege
okalways is false and autonomous invocation is allowed (platform default). The skill does not request permanent presence or system-wide changes; nothing in the package attempts to modify other skills or global agent settings.