Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Mercury Payments
v1.0.1Pay invoices via Mercury Bank API. Use when sending ACH or wire payments through Mercury, creating recipients, querying transactions, or managing payment wor...
⭐ 0· 661·0 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
SKILL.md describes paying invoices via the Mercury API (create recipients, send ACH/wire, query transactions) which matches the name/description — however the instructions require a Mercury API token and access to invoice emails/password vaults, but the registry metadata declares no required env vars or credentials. The missing declaration is an incoherence.
Instruction Scope
Instructions go beyond calling the Mercury API: they tell the agent to find invoice emails, download attachments to /tmp/, reply in existing email threads, and email bookkeeping/vendor addresses. These steps imply mailbox access and local file handling that are not described in the manifest and broaden the skill's scope and data access significantly.
Install Mechanism
Instruction-only skill with no install spec and no code files — lower disk/write risk. There is nothing being downloaded or installed by the skill itself according to the manifest.
Credentials
SKILL.md explicitly expects a Mercury API token ($MERCURY_API_TOKEN) and even suggests using 'pass show <vault-path>' for secrets, yet the registry lists no required env vars or primary credential. The instructions also handle bank account numbers, routing numbers, and instruct emailing/attaching sensitive PDFs — all sensitive operations that should be declared and scoped in the manifest.
Persistence & Privilege
The skill does not request always:true and is user-invocable (default). It instructs logging payments to a 'daily memory file' and sending emails; this is normal for a payments workflow but increases audit requirements. Ensure the agent cannot autonomously send funds without the explicit operator approval the SKILL.md demands.
What to consider before installing
Do not install yet — the skill's instructions require a Mercury API token and access to email/password stores but the registry metadata does not declare these requirements. Before proceeding: (1) ask the publisher to update the manifest to declare MERCURY_API_TOKEN (and any mail or vault config paths) so you can assess least-privilege; (2) verify how the agent will obtain invoice emails and send outgoing mail (which mailbox credentials are needed and where those will be stored); (3) ensure human-in-the-loop enforcement so payments cannot be made autonomously (audit/log every payment and require explicit operator confirmation); (4) provide the minimal-scope API token (write-limited to needed accounts) and test against a sandbox Mercury account first; and (5) confirm handling of invoice PDFs and bank account data meets your data-protection policies (avoid storing sensitive attachments in persistent, unencrypted memory). If the publisher cannot clarify or update the manifest to match the SKILL.md, treat the skill as risky and avoid granting mailbox/vault access or payment credentials.Like a lobster shell, security has layers — review code before you run it.
latestvk9753asmw3zrhfh0yctggzkxjx8254ek
License
MIT-0
Free to use, modify, and redistribute. No attribution required.