Back to skill

Security audit

insight-ecom-oracle

Security checks for vulnerabilities and agentic risk

Overview

This paid prompt-search skill has real review concerns because it sends user queries and IDs to a hardcoded external service, redirects users to a payment page, and requests broad execution authority.

Review this skill before installing. It is not showing destructive or backdoor behavior, but users should understand that searches and user identifiers go to a third-party endpoint, access is tied to an external payment flow, and the manifest asks for exec despite no clear need in the visible code. Install only if you trust the publisher, endpoint, and payment destination, and avoid entering confidential business ideas unless the data handling terms are clear.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (4)

T01 · Skill Instruction Hijacking

Warning
Location
scripts/main.py:156
Finding

Persistent Commercial Output Injection and Payment Redirection

Content
View full analysis
Remediation
View remediation

other

Warning
Location
scripts/main.py:20
Finding

Search Queries and User Identifiers Disclosed to an External Gateway

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/main.py:220
Finding

Untrusted Remote Content Rendered Without Markdown Sanitization

Content
View full analysis
= max_results: break continue ``` ```python for i, item in enumerate(prompts, 1): # item = {title, content, category} title = item.get('title', '') if isinstance(item, dict) else '' content = item.get('content', item) if isinstance(item, dict) else item category = item.get('category', '') if isinstance(item, dict) else '' cat_label = f"📂 {category} |" if category else "" body_lines.append(f"**【{i}】** {cat_label} **{title}**\n") # Full master_prompt in markdown code block, fully visible body_lines.append(f"```\n{content}\n```\n") body_lines.append("") ``` ### Technical Analysis The remote gateway controls the `title`, `category`, and `content` fields. These values are accepted with only basic type and length checks and are interpolated directly into Markdown. Wrapping `content` in triple backticks is not sufficient sanitization. A value containing its own triple-backtick sequence can terminate the intended code block and inject arbitrary Markdown outside it. The `title` and `category` fields are rendered directly into emphasized Markdown without escaping, so they can also introduce links, mentions, formatting, or misleading instructions. This is a content-injection flaw rat ...[truncated 1352 chars]
Remediation
View remediation

T08 · Insecure Dependencies

Note
Location
skill.yml:46
Finding

Unpinned Third-Party Python Dependency

Content
View full analysis
=3.8" pip: - requests ``` ### Technical Analysis The `requests` dependency is specified without an exact version or integrity hash. Consequently, installations performed at different times can resolve to different package versions. This weakens build reproducibility and prevents the reviewed source tree from uniquely defining the runtime dependency set. No evidence in the reviewed project shows that the named `requests` package is malicious. The risk arises from unconstrained future resolution, accidental incompatibility, repository compromise, or an unreviewed release being installed automatically. The broad Python constraint also permits multiple interpreter versions, although the primary supply-chain concern is the unpinned package. ### Attack Path 1. The skill is installed in a new environment. 2. The package installer resolves `requests` without an exact version or hash. 3. A release not covered by the original audit is selected. 4. If that release or its dependency chain is compromised or behaviorally incompatible, its code executes when imported by `scripts/main.py`. 5. The dependency runs with the same process privileges as the skill. ### Impact Assessment If a resolved dependency were compromised, it could theoretically access the same network, environment, and filesystem resources available to the Python process. The current repository does not demonstrate such a compromise, so the present finding is a preventive supply-chain weakness with low immediate risk. ]]>
Remediation
View remediation
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Findings (18)

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding

The skill is presented as a prompt-retrieval assistant, but its documented workflow also generates user IDs, gates content on registration/payment state, and directs users to a third-party payment flow. This mismatch is dangerous because it hides material behavior from both users and platform reviewers, increasing the risk of deceptive monetization, unauthorized data handling, and misuse of the skill as a payment funnel.

Content

No source excerpt is available for this finding.

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 · scripts/main.py (reported line 46)May include surrounding context.

python
elif isinstance(item, str):
                if len(item) > 200 and 'Role' in item:
                    prompts.append(item)
        return prompts

    # data 是字符串
    if not data or not isinstance(data, str):

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 · scripts/main.py (reported line 70)May include surrounding context.

python
elif isinstance(item, str):
                if len(item) > 200 and 'Role' in item:
                    prompts.append(item)
        return prompts

    # data 是字符串
    if not data or not isinstance(data, str):

Vague Triggers

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The trigger phrases include extremely broad terms such as 想要 and 获取, which are common in normal conversation and can cause accidental or adversarial activation outside the intended e-commerce prompt-retrieval context. Over-broad activation increases the chance that the skill is invoked on unrelated user content, potentially exposing privileged tools or returning unintended prompt material.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding

The skill describes calling an external LAF API but does not declare any tool scope or allowed network permissions. This creates a transparency and governance gap: the host or reviewer cannot clearly constrain or audit outbound access, and users are not informed that their queries may be transmitted externally.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The description, triggers, usage instructions, and output templates are entirely in Chinese and present the skill's interaction model in a single language with no opt-in or alternative locale support. Under the policy, forcing a specific language without user choice is a natural-language policy violation unless the locale restriction is explicitly justified.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

Several trigger patterns are broad natural-language phrases and regex-like forms such as '想要.*的提示词' and '获取.*的架构', which can match many ordinary requests outside the intended narrow skill scope. Overbroad activation can cause unintended invocation, sending unrelated user queries into external retrieval or payment-gated flows without clear intent.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The workflow states that the skill will automatically generate a user ID and perform external API/payment processing, but it does not provide a clear user-facing disclosure about what data is collected, where it is sent, or how it is used. In context, this is more dangerous because the skill combines identity generation, search telemetry, and third-party payment redirection, which can expose users to privacy loss and social-engineering-style monetization without informed consent.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

A hardcoded payment URL is embedded directly in a prompt-search skill, which is not necessary for simple retrieval functionality. In this context, the skill can steer users to an external payment flow from within the agent, increasing the risk of deceptive monetization or abuse if the endpoint changes or is not independently verified.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The code transmits the user's search query and user ID to an external service without any in-file disclosure or consent mechanism. Because queries may contain sensitive commercial ideas or personal identifiers, this creates a privacy and data-governance risk, especially when the service is third-party hosted.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
96% confidence
Finding

This outbound request sends user-supplied query data and a user identifier to an external host. In a skill that claims to retrieve prompts, such transmission is contextually sensitive because users are not clearly informed that their input and account linkage are being shared off-platform.

Content

Scanner excerpt · scripts/main.py (reported line 24)May include surrounding context.

python
"""单次搜索调用"""
    payload = {"action": "search", "query": query, "user_id": user_id}
    try:
        response = requests.post(LAF_URL, json=payload, timeout=10)
        return response.json()
    except Exception:
        return None

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill goes beyond its stated purpose of searching and returning e-commerce prompts by implementing registration state handling, paywall enforcement, payment-link distribution, and activation messaging. This is risky because it can monetize or gate access through the agent interface without clear platform-level disclosure or trust guarantees, creating phishing, policy, and user-manipulation concerns.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

All user-facing status and instruction messages in this file are presented in Chinese, including registration, payment, and result text, with no apparent option for the user to choose another language. That constitutes a language/locale constraint in natural-language behavior without documented opt-in or justification.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The payment-status check sends the same query and user ID to the external endpoint again, even though only account status appears necessary. This expands unnecessary data exposure and couples access control with content queries, increasing privacy risk and data collection beyond what is needed.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
96% confidence
Finding

This second outbound request duplicates transmission of query and user ID to the same external service for status checking. The duplicate transfer is unnecessary for least-privilege data handling and broadens third-party visibility into user behavior and billing-related metadata.

Content

Scanner excerpt · scripts/main.py (reported line 203)May include surrounding context.

python
# ==================== 步骤3:检查支付状态 ====================
    check_payload = {"action": "search", "query": query, "user_id": user_id}
    try:
        check_response = requests.post(LAF_URL, json=check_payload, timeout=10)
        check_data = check_response.json()
        check_status = check_data.get("status") or check_data.get("ec")
    except Exception:

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
81% confidence
Finding

The visible name and description are entirely in Chinese, with no indication that users may choose another language or that the skill is intentionally restricted to a Chinese-speaking audience for a documented reason. This can constitute a language/locale policy issue because the skill presentation implicitly enforces one language without opt-in or justification.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The invocation configuration defines positive triggers and regex patterns but provides no scope boundaries, exclusions, or examples of when the skill must not run. In combination with broad triggers, this makes misrouting more likely and can route unrelated user input into a skill that may possess elevated capabilities, which is especially concerning here because the manifest also requests exec.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The manifest requests the exec capability even though the skill is described as a prompt/search retrieval assistant and does not document any legitimate need for shell execution. Unnecessary command-execution privileges materially expand the attack surface: if later skill logic interpolates user-controlled input into shell commands, this can enable arbitrary command execution, data access, or lateral abuse of the host environment.

Content

No source excerpt is available for this finding.