Back to skill

Security audit

DocuSign

Security checks for vulnerabilities and agentic risk

Overview

The skill’s DocuSign access and sending behavior fit its stated purpose and require clear user intent before changes.

Connect the intended DocuSign account and protect its stored OAuth credentials. Confirm the template and recipients before authorizing the send tool: it sends immediately and offers no draft or preview stage.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/server.py
Finding

Envelope sending bypasses the documented confirmation requirement

Content
View full analysis

Impact

An invocation made while preparing or reviewing an agreement can prematurely deliver signing requests and template documents to the supplied recipients, using the connected account.

Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 38)May include surrounding context.

Quick start

This skill is a thin pass-through to a local stdio MCP server. mcporter spawns the skill's Python server on each call, refreshes the OAuth access token when needed, and injects the fresh token into the server env.

sh
mcporter --config {baseDir}/mcporter.json list maverick-docusign --schema

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 69)May include surrounding context.

md
- `MAVERICK_DOCUSIGN_MCP_EXPIRES_IN`
- `MAVERICK_DOCUSIGN_MCP_REFRESH_TOKEN_EXPIRES_AT`

mcporter refreshes expired DocuSign access tokens through DocuSign's token endpoint before spawning the stdio server, then injects the token into `MAVERICK_DOCUSIGN_MCP_ACCESS_TOKEN`. If calls keep returning auth errors after retry, the OAuth grant has likely been revoked or expired; reconnect the integration.

## Data flow

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: env.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.