Back to skill

Security audit

Ai Engineering Legal

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only Chinese construction cost and legal workflow skill with no code execution, persistence, or hidden data movement, though users should be careful with sensitive case materials.

Before installing, treat outputs as drafting and risk-screening assistance rather than legal advice. Do not paste unredacted contracts, signatures, seals, identity data, account details, privileged communications, sealed case materials, or trade secrets unless your environment is approved for that data. For major disputes or filing-ready documents, have a qualified lawyer or cost-appraisal professional review the result.

Vulnerability Patterns
  • 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
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (8)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The README defines very broad trigger phrases such as '造价+法律', '合同风控', and '证据评估' without any activation boundaries, routing rules, or disambiguation criteria. In a skill that influences legal and cost-analysis workflows, this can cause unintended invocation in unrelated conversations and lead users to receive authoritative-seeming legal/cost guidance when they did not explicitly request this skill.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill advertises activation with open-ended language such as '包括但不限于' and broad scenario coverage, which can cause the agent to invoke this legal-analysis skill for loosely related prompts. In a domain involving contracts, disputes, evidence, and judicial appraisal, over-triggering increases the chance of unnecessary exposure of sensitive case materials and overreliance on specialized legal reasoning when a narrower skill or safer fallback would be more appropriate.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill instructs users to provide contracts, change orders, settlement documents, and evidence materials but does not prominently warn against submitting personal data, confidential business records, or privileged case content. Because the skill is designed for legal disputes and judicial appraisal preparation, users are especially likely to paste highly sensitive documents, making omission of handling guidance materially risky.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The line “代码注释使用中文” mandates a specific language for code comments, which is a natural-language policy constraint. The README does not present this as optional or justified by a documented locale-specific requirement, so it appears to force a language choice without opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The document presents all instructions and example content exclusively in Chinese, with no note that the skill is Chinese-language only or that users can choose another language. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

This markdown file presents all instructions and outputs exclusively in Chinese, with no indication that users can choose another language or that the locale restriction is intentional. Under the policy, forcing a specific language without user opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
87% confidence
Finding

This markdown file presents all guidance exclusively in Chinese and does not state that the skill is China-specific or that users may choose another language. Under the language/locale policy, forcing a specific language without user opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

This markdown template is entirely written as a fixed Chinese-language document structure and does not indicate that users may choose another language or locale. Under the policy rule for language/locale constraints, a skill should either offer user choice or clearly document that the skill is specifically intended for a Chinese-language/legal context.

Content

No source excerpt is available for this finding.