review-fto-report-quality-ip

• Outcome: Pass
• Latest audit: Sep 16, 2026 · 11:08 AM UTC
• Version: 1.0.0

Overview

This skill is a coherent FTO report-quality review tool with disclosed local report generation, validation scripts, and optional PatSnap patent-search connectors.

Install only if you are comfortable having the agent process FTO reports and product/patent search details. Use the optional PatSnap connectors only for information you are permitted to send to that provider, and keep API keys out of reports and input files as the skill instructs.

A.I.G

Vulnerability Patterns

• 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
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• System Prompt Leakage: Direct Leakage, Indirect Extraction, Tool-Based Exfiltration
• 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 (8)

Direct Prompt Extraction

High

• Category: System Prompt Leakage
• Confidence: 85% confidence

Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · SKILL.md (reported line 177)May include surrounding context.

md

| FTL-06 | A known higher-risk finding is omitted or contradicted without explanation | Decision-makers receive a materially distorted picture |
| FTL-07 | The report gives an absolute non-infringement assurance unsupported by scope and law | The conclusion exceeds the evidence |

### Output rule

- show a prominent text-labeled fatal banner at the top;
- state each fatal defect and its evidence;

Undeclared Tool Scope

Medium

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

Finding

The skill instructs use of local scripts, HTML generation/validation, and external connectors, which implies file read/write and network-capable execution, but it does not declare an explicit tool/permission boundary. In an agent environment, missing scope declarations can let the runtime grant broader-than-necessary access, increasing the chance of unintended file access, data exfiltration, or unsafe connector use when handling sensitive legal documents.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

• Category: Not specified by scanner
• Confidence: 96% confidence

Finding

The markdown explicitly requires output to use English labels and lang="en", which imposes a specific language choice. Under the policy rule, forced language selection is a violation unless the skill offers opt-in/choice or clearly justifies the locale restriction as necessary for a region-specific tool.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

• Category: Not specified by scanner
• Confidence: 94% confidence

Finding

The markdown states the report should 'use English professional terminology,' which imposes a specific language requirement as a general standard. The document does not offer user choice or clearly justify this locale constraint as limited to a specific regional compliance context.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

• Category: Not specified by scanner
• Confidence: 95% confidence

Finding

The code checks specifically for <html lang="en">, causing non-English reports to fail this structural validation. Under the language/locale policy rule, forcing a specific language without user opt-in or a clearly documented justification is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

• Category: Not specified by scanner
• Confidence: 91% confidence

Finding

The generated HTML report is emitted with lang="en" and fixed English labels such as "Validation summary" and "Check register". This enforces a specific language in the user-facing output without offering locale selection or explicit opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

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

Finding

The phrase "localized international edition" indicates a locale-specific variant, but the document does not explain what locale constraints apply or offer any user opt-in or choice. Under the language/locale policy rule, forcing or implying a specific locale without explicit user choice can be a policy concern.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low

• Category: Not specified by scanner
• Confidence: 77% confidence

Finding

This code creates an output directory and writes both JSON and HTML files, which is a file-modifying operation covered by the missing-warning rule for code files. While the module docstring documents the outputs, there is no runtime confirmation or user-facing notice at the point of write, so users may not be explicitly warned that files will be created in a derived directory.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.