T01 · Skill Instruction Hijacking
- Location
scripts/compare_policies.py:409- Finding
Hard-Coded Commercial Steering When Reputation Data Is Unavailable
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
The skill is a coherent insurance-policy comparison helper, but it handles sensitive documents and creates an auto-opened HTML report with unsafe templating and remote JavaScript, so it should be reviewed before use.
Review this skill before installing. Use it only if you are comfortable uploading or extracting insurance policy data, sending insurer/product names to external searches, and creating a persistent local HTML report. Prefer requiring confirmation before searches and file creation, disabling auto-open, escaping all report content, and bundling or integrity-pinning the chart library.
scripts/compare_policies.py:409Hard-Coded Commercial Steering When Reputation Data Is Unavailable
assets/template.html:78Stored HTML and JavaScript Injection Through Unescaped Report Placeholders
assets/template.html:7Remote JavaScript Is Executed Without Integrity Verification
Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.
The documented behavior promises OCR, policy parsing, real-time reputation searches, and visual report generation, but the analyzed capability does not implement those features. This mismatch is dangerous because users and orchestrators may make trust decisions based on false assumptions, causing sensitive insurance documents to be handled in ways not actually supported or audited, and undermining security review of the real behavior.
The trigger conditions are so broad that ordinary insurance questions may invoke the skill unexpectedly, increasing the chance that users disclose policy documents or personal insurance details without intending to activate document-processing logic. Over-broad activation expands the attack surface and can lead to unintended data handling.
YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).
.append(f"{prefix} 🔴 有投诉 **以各种理由拒赔**")
# 生成场景建议
recommendations = []
ded_a = policy_a.get("dimensions", {}).get("deductible_and_waiting", {}).get("medical_deductible", 999)
ded_b = policy_b.get("dimensions", {}).get("deductible_and_waiting", {}).get("medical_deductible", 999)
if ded_a == 0 and ded_b > 0:
recommendations.append(("👨💻", "如果你是 **办公室上班族** → 选保单A,0免赔,日常小意外最实用"))
elif ded_b == 0 and ded_a > 0:
recommendations.append(("👨💻", "如果你是 **办公室上班族** → 选保单B,0免赔,日常小意外最实用"))
traffic_a = policy_a.get("dimensions", {}).get("coverage_scope", {}).get("traffic_extra", {})
traffic_b = policy_b.get("dimensions", {}).get("coverage_scope", {}).get("traffic_extra", {})
a_traffic_max = max((v.get("amount") or 0 for v in traffic_a.values() if isinstance(v, dict)), default=0)
b_traffic_max
The skill describes file-writing behavior (saving an HTML report to the user's desktop) but does not declare any tool scope or permissions boundary. This creates an authorization and transparency gap: a host may permit broader file operations than users expect, and reviewers cannot verify that filesystem access is intentionally constrained.
文件标题、描述、流程、示例和注意事项均以中文固定呈现,并在 L131 要求“所有术语需提供白话解释”,但没有说明是否支持其他语言或允许用户选择输出语言。对于通用技能,这种隐含的单一语言约束可能构成语言/locale 策略问题。
The skill proposes real-time searches across external sites for claim reputation but does not clearly disclose that insurer/product-related queries will be sent to third-party services. Even if the query is not highly sensitive, external transmission can leak user intent, business interest, or document-derived entities and may violate privacy expectations or enterprise network policy.
Saving an HTML report to the desktop and automatically opening it without an explicit prompt is risky because it performs local side effects on the user's system and may expose sensitive policy data in a persistent, easily discoverable location. Auto-opening generated HTML also increases exposure to unsafe rendering behaviors if any untrusted content is embedded in the report.
The HTML document explicitly sets lang="zh-CN", and the visible interface text throughout the template is only in Simplified Chinese. This indicates a fixed language/locale experience without any user opt-in or documented justification, which matches the policy-violation category for forced language or locale.
The file title and all operational guidance are written exclusively in Chinese, with no indication that other languages are supported or that Chinese is a region-specific requirement. Under the policy rule for language or locale constraints, this is a natural-language policy issue because the skill appears to require a specific language without user opt-in.
The skill explicitly directs real-time searches across social media, complaint platforms, and regulator sites to assess claim reputation, but the configuration shown does not require a user-facing disclosure or consent flow before external data access occurs. In a policy-analysis workflow that may involve insurer/product names derived from uploaded documents, this can surprise users, expand data exposure to third parties, and create privacy/compliance risk even if only partial identifiers are queried.
The schema title, field descriptions, and terminology mapping are entirely written in Chinese, and the file defines output content such as explanatory text and notes in Chinese only. Because the file provides no opt-in, alternative locale, or stated region-specific justification, it appears to impose a specific language/locale policy on users.
This code file contains user-facing natural-language descriptions and output strings exclusively in Chinese, including the module description and CLI help text. Under the policy rule for language/locale, forcing a specific language without user opt-in can be a natural-language policy violation when no locale choice or justification is provided.