Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
CreditClaw
v2.9.9Shop in any store with any payment method.
⭐ 5· 1.5k·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (agent checkout and payments) align with what the skill requests and documents: only CREDITCLAW_API_KEY is required and all endpoints are for creditclaw.com. The included guides (platform detection, checkout flows, webhooks, wallet rails) are appropriate for a checkout/payment integration.
Instruction Scope
SKILL.md and companion guides instruct the agent to request approvals, fetch a single-use decryption key, decrypt card data in memory, and inject card fields into merchant pages via browser automation. This is expected for a checkout skill but involves handling very sensitive data (card numbers, CVV). The skill repeatedly warns not to leak the API key and to discard decrypted card data. It also references a plugin (creditclaw_fill_card) for safer handling but the skill bundle does not include executable plugin code — the guide assumes a separate plugin may be present.
Install Mechanism
Instruction-only skill with no install spec and no binaries. Nothing is downloaded or written to disk by the skill package itself, which minimizes supply-chain risk.
Credentials
The single required environment variable (CREDITCLAW_API_KEY) is proportional to the declared purpose. No unrelated credentials, system paths, or broad secrets are requested.
Persistence & Privilege
The skill is not marked always:true and uses user_confirmed invocation/default approval_mode ask_for_everything. Model invocation is allowed (the platform default) but there are no unusual persistent privileges requested by the skill itself.
Assessment
This skill is internally consistent for an agent-based checkout/payment integrator, but it handles very sensitive data (card numbers, CVV) and your CREDITCLAW_API_KEY is effectively the bot's spending credential. Before installing: 1) Only provide CREDITCLAW_API_KEY if you trust creditclaw.com and the team operating it; 2) Keep approval_mode set to require owner confirmation for purchases until you fully trust and audit the workflow; 3) Verify how your platform stores the API key and webhook secret (use a secure secrets manager and do not log them); 4) Note the skill references a plugin to keep card data out of agent context — confirm whether that plugin is actually installed and trusted in your environment (the skill package does not include executable plugin code); 5) If you allow autonomous invocation, be aware the agent will be able to initiate checkout flows that use your provided API key (the skill enforces owner approval server-side by default, but that increases the blast radius if misconfigured).Like a lobster shell, security has layers — review code before you run it.
agentvk97c68p1htb7yyee5faga5hdy582wbvnagentsvk97c68p1htb7yyee5faga5hdy582wbvnamazonvk978ttsjr1s2n0ad88180q92sd82qh8vanywherevk97c68p1htb7yyee5faga5hdy582wbvnbuyvk9773wgzx93nq7yenx5xm7z8px83mzv0cardvk9773wgzx93nq7yenx5xm7z8px83mzv0creditcardvk9773wgzx93nq7yenx5xm7z8px83mzv0creditclawvk97fg9fd41fn7rvtmbfzrv6stn834ejjlatestvk9773wgzx93nq7yenx5xm7z8px83mzv0ordervk978ttsjr1s2n0ad88180q92sd82qh8vpayvk97c68p1htb7yyee5faga5hdy582wbvnpaymentsvk9773wgzx93nq7yenx5xm7z8px83mzv0shopvk9773wgzx93nq7yenx5xm7z8px83mzv0shopifyvk9773wgzx93nq7yenx5xm7z8px83mzv0shoppingvk9773wgzx93nq7yenx5xm7z8px83mzv0stripevk9773wgzx93nq7yenx5xm7z8px83mzv0x402vk9773wgzx93nq7yenx5xm7z8px83mzv0
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
EnvCREDITCLAW_API_KEY