Contract Risk Review

• Outcome: Review
• Latest audit: Jul 24, 2026 · 1:01 AM UTC
• Version: 1.1.2

Overview

The skill is a contract-review SaaS client, but it sends sensitive contract text to an under-disclosed plain-HTTP backend rather than the documented DeepSeek URL.

Install only if you are comfortable sending contract text and your user key to the publisher's remote service. Redact company names, personal data, amounts, and confidential terms first, and avoid using it for sensitive contracts unless the publisher provides HTTPS, accurate backend disclosure, and clear data-handling terms.

SkillSpector

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands

Findings (5)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 91% confidence
• Finding: The skill requires an API key from the environment and explicitly documents outbound calls to a third-party DeepSeek endpoint, but the skill file does not declare permissions for secrets or network access. That mismatch is dangerous because users and hosting platforms may not realize the skill can transmit contract contents and sensitive data to an external service, creating a transparency and data-governance risk rather than a direct exploit primitive.

Description-Behavior Mismatch

Medium

• Confidence: 92% confidence
• Finding: The skill is presented as a contract review tool, but it also includes account registration and account/billing-related functionality that expands behavior beyond the advertised purpose. This increases data-sharing and service-coupling risk because users may interact with a third-party commercial backend without a narrowly scoped contract-review-only interface.

Context-Inappropriate Capability

Medium

• Confidence: 89% confidence
• Finding: The `services` command enumerates a broader catalog of backend AI services unrelated to contract review, showing that this skill can act as a discovery interface for external capabilities beyond its stated scope. That broader access violates least functionality and may expose users to unintended workflows, billing, or data transfers.

Missing User Warnings

Medium

• Confidence: 98% confidence
• Finding: The tool sends full contract text to an external backend for analysis, but there is no explicit warning, consent prompt, or privacy notice despite contracts often containing confidential business terms, personal data, or legal secrets. Because the default backend is a hard-coded remote IP over plain HTTP, the sensitivity of the transmitted content makes this especially dangerous.

External Transmission

Medium

• Category: Data Exfiltration

Content

if method == "GET":
            resp = requests.get(url, headers=h, params=data or {}, timeout=30)
        else:
            resp = requests.post(url, headers=h, json=data or {}, timeout=60)
        if resp.status_code >= 400:
            try:
                err = resp.json()

• Confidence: 97% confidence
• Finding: The code transmits data to an external backend, including contract text and possibly account identifiers, which creates a real confidentiality risk. In this skill context, users are likely to submit highly sensitive legal documents, so off-system transmission materially increases exposure and trust requirements.

Static analysis

No suspicious patterns detected.