Mercury Payments

Pay invoices via Mercury Bank API. Use when sending ACH or wire payments through Mercury, creating recipients, querying transactions, or managing payment wor...

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.

Type: OpenClaw Skill Name: mercury-payments Version: 1.0.1 The skill is classified as suspicious primarily due to the explicit example of `curl ... | python3 -c "..."` in `SKILL.md`. While presented as a placeholder, this pattern demonstrates a direct command injection vulnerability (potential RCE) if the `...` portion is controlled by a malicious prompt. This high-risk execution pattern, combined with the skill's inherent ability to perform sensitive financial transactions, access API tokens (e.g., via `pass show <vault-path>`), and interact with the file system (`/tmp/`, 'daily memory file'), elevates its risk profile beyond benign, even without clear evidence of intentional malicious payloads within the provided bundle.