Pandadoc mcp

PassAudited by ClawScan on May 10, 2026.

Overview

The skill is a coherent PandaDoc OAuth/MCP integration with no malicious behavior found, but it handles sensitive PandaDoc credentials and data and uses an unpinned mcporter dependency.

Before installing, confirm that you trust the Maverick/OpenClaw runtime and the active PandaDoc tool provider with your PandaDoc documents and OAuth access. Consider pinning the mcporter package version, protecting the local mcporter credential vault, and approving only clearly requested write actions such as sending, updating, or deleting documents.

Findings (5)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

If used carelessly, the agent could change or send PandaDoc documents in ways visible to customers or recipients.

Why it was flagged

The skill acknowledges that PandaDoc tools may perform high-impact account mutations, while also instructing the agent to get clear user intent first.

Skill content
Write operations that create, send, update, complete, delete, or modify documents, templates, recipients, proposals, or document status can affect customer-visible signing workflows. Confirm clear user intent before invoking write tools
Recommendation

Only allow write actions after reviewing the target document/template and explicitly confirming the action with the user.

What this means

Installing or enabling the skill gives the agent access through PandaDoc OAuth credentials provisioned by Maverick.

Why it was flagged

The skill requires OAuth credential environment variables for PandaDoc. This is expected for the integration, but it grants access to the user's PandaDoc account data and actions.

Skill content
"MAVERICK_PANDADOC_MCP_REFRESH_TOKEN", "MAVERICK_PANDADOC_MCP_CLIENT_ID", "MAVERICK_PANDADOC_MCP_ACCESS_TOKEN"
Recommendation

Use a PandaDoc authorization with the minimum needed account privileges and revoke the integration if it is no longer needed.

What this means

Anyone or anything with access to that local credential file may be able to use the PandaDoc OAuth tokens.

Why it was flagged

The initializer writes the supplied access and refresh tokens into a local mcporter credential file. This is normal OAuth wrapper behavior, but it creates persistent local credential material.

Skill content
mcp_vault="${HOME}/.mcporter/credentials.json" ... tokens:     {access_token: env.mcp_access, refresh_token: env.mcp_refresh, token_type: "Bearer"}
Recommendation

Keep the runtime home directory protected, avoid sharing the mcporter credential vault, and rotate/revoke tokens if the environment is compromised.

What this means

Future npm package changes could affect the behavior of the installed mcporter CLI.

Why it was flagged

The skill depends on an external npm package installed at the latest version. The artifact discloses this and recommends pinning for stricter controls.

Skill content
Auto-installed via `npm install -g --ignore-scripts mcporter` if missing on PATH ... The install spec uses unpinned `mcporter` (npm `latest`)
Recommendation

Pin mcporter to a reviewed version in controlled environments.

What this means

PandaDoc document and workflow data may be processed by the active MCP/tool provider for the integration.

Why it was flagged

The data flow to the active tool provider is disclosed and purpose-aligned, but it involves sensitive PandaDoc business data and the repository does not include a provider-owned PandaDoc MCP manifest.

Skill content
Runtime tool calls, if present in the active OpenClaw environment, use Maverick-provisioned OAuth credentials and expose PandaDoc document, template, recipient, proposal, and status data to the active tool provider.
Recommendation

Use the skill only for PandaDoc-related tasks and avoid sending unrelated sensitive content through the tools.