Security audit

prospect-landing-research

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed sales-research skill for Chinese-market account planning, with web research and contact discovery that fit its purpose but should be used deliberately.

Install this for Chinese-language or China-market sales account research where public web research and contact-path discovery are expected. Review the auto-detect behavior before enabling it broadly, and use care with personal contact details, logged-in recruiting or social platforms, and jurisdiction-specific compliance rules.

A.I.G

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

SkillSpector

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 (6)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill defines a very broad set of trigger phrases such as '刚上手', '客户调研', '怎么联系', and '想切入', many of which are common in ordinary sales conversations and not unique to this skill's narrow purpose. Because the skill also performs outbound web research and structures account-targeting guidance, unintended invocation could cause unnecessary data collection, confusing routing, or execution of a more powerful workflow than the user intended.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: Auto-detection is enabled while the activation criteria remain ambiguous, and the skill has outbound network access via web_search and web_fetch. This combination increases the chance that routine sales discussion will silently trigger external research and produce sensitive prospecting guidance without a clearly expressed user request, creating over-collection and misrouting risk.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: This file’s natural-language instructions are entirely in Chinese, and there is no indication that the skill is limited to Chinese-speaking users or that language selection is optional. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: This file hard-codes China-specific and Chinese-language data sources as the default research hierarchy without any locale gating, user consent, or documented opt-in. In an agent skill, that can cause inappropriate source selection, privacy/compliance mismatches, and biased or unusable outputs when the user, target entity, or jurisdiction is not China-specific.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The entire skill reference is written only in Chinese and includes China-specific operating assumptions such as '中国中层网上搜不到是常态' and references to Chinese platforms and regulations. Under the stated policy, forcing a specific language or locale without user choice or explicit justification is a natural-language policy violation.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The file title and introductory text are entirely in Chinese and frame the document as the required delivery template, which implies a fixed language/locale for use. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is explicitly justified.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.