ClawHub
Back to skill

Security audit

广告洞察中枢LITE

Security checks for vulnerabilities and agentic risk

Overview

This skill appears to be a legitimate AdMapix advertising-data query helper, but it asks for broader command and file-writing authority than its stated API-query purpose needs.

Review this skill before installing. It likely performs the advertised AdMapix queries, but install it only if you are comfortable granting command execution and potential file-write authority, and avoid entering sensitive campaign, customer, or business secrets in search terms sent to AdMapix.

A.I.G

Vulnerability Patterns
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
  • 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
Findings (1)

T05 · Unauthorized Access and Privilege Escalation

Warning
Location
SKILL.md:6
Finding

Overprivileged and Inconsistent Tool Permissions

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (10)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The activation language is very broad, covering common marketing, growth, and promotion scenarios rather than a tightly bounded API-query task. Broad triggers can cause the agent to invoke this skill in contexts where external transmission and exec access are unnecessary, increasing exposure of user data and misuse of capabilities.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The description explicitly states '支持中文交互' and the document consistently presents Chinese-only interaction guidance, but it does not offer users a language choice or describe this as an optional locale preference. This can violate language/locale policy when a skill implicitly constrains interaction language without user opt-in.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill declares write capability even though its stated function is querying a remote API and returning structured results. Unnecessary write access violates least privilege and could let the agent modify local files or persist data without a clear operational need.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill advertises write-capable automated file handling without clearly warning users that local data may be modified. In a tool-enabled agent environment, undisclosed file modification capability can surprise users and create integrity risks, especially because the skill's main purpose does not require file writes.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 121)May include surrounding context.

bash
# 搜索美国地区游戏类视频广告创意
curl -s -X POST "https://api.admapix.com/api/data/search" \
  -H "X-API-Key: ${ADMAPIX_API_KEY}" -H "Content-Type: application/json" \
  -d '{"keyword":"puzzle","countries":["US"],"trade_level1":["602"],"adTypes":["010"],"page":1,"page_size":10}'

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 121)May include surrounding context.

bash
# 搜索美国地区游戏类视频广告创意
curl -s -X POST "https://api.admapix.com/api/data/search" \
  -H "X-API-Key: ${ADMAPIX_API_KEY}" -H "Content-Type: application/json" \
  -d '{"keyword":"puzzle","countries":["US"],"trade_level1":["602"],"adTypes":["010"],"page":1,"page_size":10}'

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 151)May include surrounding context.

bash
# 搜索美国地区游戏类视频广告创意
curl -s -X POST "https://api.admapix.com/api/data/search" \
  -H "X-API-Key: ${ADMAPIX_API_KEY}" -H "Content-Type: application/json" \
  -d '{"keyword":"puzzle","countries":["US"],"trade_level1":["602"],"adTypes":["010"],"page":1,"page_size":10}'

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill gives contradictory safety guidance: earlier it says not to use ping for connectivity checks, but later error handling instructs the agent to execute ping. In an exec-capable skill, inconsistent command guidance is dangerous because it normalizes unnecessary shell execution and can lead to unsafe or noncompliant troubleshooting behavior.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The documentation broadens the skill from a narrowly scoped ad-intelligence API client into generic automation, file handling, and command execution. That scope expansion increases the chance an agent will apply the skill to unrelated tasks and exercise powerful capabilities beyond what users would reasonably expect.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill sends user-supplied query data to a third-party API but does not prominently warn users that their input will leave the local environment. This is dangerous because users may include sensitive campaign, app, or business data without understanding it will be transmitted externally.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.