Agentic Contract Skill

• Outcome: Pass
• Latest audit: Sep 16, 2026 · 8:56 AM UTC
• Version: 1.0.9

Overview

This is a local contract document generator with expected file-writing behavior, but users should choose output paths carefully because generated files can replace existing files.

Install only if you are comfortable with a local generator that saves contract details, including contact information and terms, into PDF and Markdown files. Use a dedicated output folder, avoid pointing outputs at existing important files, and review generated contracts with qualified counsel before using them for a real engagement.

A.I.G

Vulnerability Patterns

• Insecure Skill Coding Practices: Finds exploitable flaws such as hardcoded secrets or command injection
• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally

Findings (1)

T09 · Insecure Skill Coding Practices

Warning

• Location: generate_contract.py:969

Finding

Unconditional Overwrite of User-Selected Output Files

Content

View full analysis

Remediation

View remediation

SkillSpector

Vulnerability Patterns

• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (6)

Ae1

High

• Category: analysis-evasion
• Confidence: 100% confidence

Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 58)May include surrounding context.

md

| `generate_contract.py` | Contract, Markdown, and envelope generator. |

Ae1

High

• Category: analysis-evasion
• Confidence: 100% confidence

Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 129)May include surrounding context.

md

| `generate_contract.py` | Contract, Markdown, and envelope generator. |

Undeclared Tool Scope

Medium

• Category: MCP Least Privilege
• Confidence: 89% confidence

Finding

The skill advertises document generation that updates configs and produces output files, but it does not declare any explicit tool scope such as permissions or allowed-tools. In an agentic environment, undeclared file-write capability weakens least-privilege controls and can let the skill modify files beyond what a reviewer or orchestrator expects.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium

• Category: Excessive Agency
• Confidence: 75% confidence

Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 89)May include surrounding context.

md

| Unknown values | Keep unknown provider, client, agreement, delivery, and agentic-development values as `TBD`. |
| Artifact status | Treat generated PDFs and Markdown as draft artifacts until the user confirms the terms and facts. |
| Skill boundary | Keep contract generation separate from proposals, invoices, delivery records, security signoff, customer success notes, email copy, and delivery packaging decisions. |
| Existing files | Do not overwrite user-specific config or generated output without checking whether it contains client-specific facts that should be preserved. |

## Configuration Toggles

Missing User Warnings

Low

• Category: Not specified by scanner
• Confidence: 83% confidence

Finding

This code writes a filled Markdown file to a user-specified path, and the rendered content is likely to include names, addresses, emails, and contract terms from the config. Although the script prints the output path afterward, there is no earlier user-facing warning, prompt, or comment near the write explaining that a plaintext copy of the contract will be saved alongside the PDF.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low

• Category: Not specified by scanner
• Confidence: 78% confidence

Finding

When enabled, the script creates a separate addressed envelope PDF using provider and client address fields, which are personal or business contact details. The operation is printed only after creation and lacks a clear prior disclosure or inline warning that another file with address data will be produced.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.