Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Imperial8629
v1.0.0Credit line service for AI agents to access x402 services without upfront payment. Use when (1) you need to call x402-enabled APIs or services but lack crypt...
⭐ 0· 217·0 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
Requiring a Node.js SDK and access to an OpenClaw agent workspace (transcripts/prompts) is consistent with a service that underwrites credit using agent behavior, but the amount of context the skill requests (execution traces, transcripts, workspace prompts) is large and not narrowly scoped to obvious underwriting data. The declared requirements (none) do not call out the filesystem access described in the instructions.
Instruction Scope
The SKILL.md instructs the agent/SDK to collect detailed agent context (session transcripts, prompts, traces) and to continuously monitor agent behavior during pre-qualification. Those instructions enable the collection of potentially sensitive data (prompts, model transcripts, environment info, and possibly secrets) beyond what a typical payment proxy would need. It does require explicit user consent for registration, which is good, but the doc lacks a precise list of fields sent to the provider and how long monitoring continues.
Install Mechanism
Installation is via npm of a scoped package (@t54-labs/clawcredit-sdk). Using npm is expected for a Node SDK but is a supply-chain risk because arbitrary code from the registry will be executed; the skill provides no checksum, source URL, or guidance to audit the package.
Credentials
The skill declares no required environment variables but instructs reading and saving credentials in ~/.openclaw/agents/<agent>/agent/clawcredit.json and accessing transcript/prompt directories (which may contain secrets). Storing API tokens to disk and recommending automatic loading increases risk if the token file isn't protected. The scope of requested filesystem access is broader than the declared metadata and could lead to exfiltration of sensitive agent data.
Persistence & Privilege
The skill is not always: true and does not request special platform privileges. However, the SDK's described behavior includes continuous monitoring during pre-qualification and automatic issuance of credit, which implies ongoing data collection across agent activity. The skill itself does not declare background services or always-on behavior, but the SDK could implement persistent monitoring once installed — the user should treat that as a significant privacy/continuity decision.
What to consider before installing
Before installing or running this skill: (1) Read the ClawCredit Privacy Policy and ask exactly what data (fields, transcripts, environment variables) the SDK will collect, and for how long; do not consent until you understand that. (2) Audit the npm package (@t54-labs/clawcredit-sdk) source code or ask for a verified source/release (repository, checksum) — npm packages are a supply-chain risk. (3) Avoid pointing transcript/prompt directories to your entire home or any directories that contain secrets; restrict to minimal, sanitized data. (4) Be cautious about auto-saving API tokens to disk — ensure the token file is protected, encrypted, or use ephemeral tokens; rotate tokens after use. (5) If possible, test in an isolated agent/workspace (sandbox) first. (6) If you lack the ability to audit the SDK, treat this as higher-risk and consider alternate payment flows or requesting the provider to disclose a minimal-data mode.Like a lobster shell, security has layers — review code before you run it.
latestvk976pwne4t4f8pmxc4v5hj5n258342ra
License
MIT-0
Free to use, modify, and redistribute. No attribution required.