Back to skill

Security audit

Maxhub Instagram

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill suspicious because its instructions include Douyin operations outside its Instagram purpose, and its installer uses an unpinned package; the scan evidence is incomplete.

Review the Douyin fallback and confirm it fits your intended use before installing. Consider whether you are comfortable running an unpinned installer and sending requests with an API key to the documented external service. The scanner analyzed all listed components, but marked the analysis partial because several references could not be resolved, so the evidence is incomplete.

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
  • 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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (6)

MCP server referenced without pinned version: 'npx clawhub'.

Medium
Category
MCP Rug Pull
Confidence
93% confidence
Finding

The installation command invokes clawhub through npx without a version pin, potentially downloading and executing a changing package release with the user's permissions. Although this is an installer rather than an MCP server reference, the underlying supply-chain risk is real if a subsequently resolved release is compromised.

Content

No source excerpt is available for this finding.

Example invocation prompts are generic words without an Instagram-specific constraint.

Medium
Category
Trigger Abuse
Confidence
95% confidence
Finding

The example prompts include 搜索 and 搜 (search), 翻译 (translate), and 用户 (user), which commonly occur in requests unrelated to Instagram. Although the README describes an Instagram assistant, these invocation examples do not require Instagram context or provide exclusions, creating ambiguity about when the skill should activate.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx clawhub'.

Medium
Category
MCP Rug Pull
Confidence
93% confidence
Finding

The documented npx command leaves the clawhub package version unspecified, allowing installation to execute a release that has not been reviewed with this skill. This is a conditional supply-chain execution risk, not evidence of an actual malicious package or an MCP server configuration.

Content

No source excerpt is available for this finding.

Example invocation phrases are generic and can collide with unrelated requests.

Medium
Category
Trigger Abuse
Confidence
97% confidence
Finding

The example commands include standalone terms such as “用户” (user), “搜索” (search), and “翻译” (translate), which commonly occur outside Instagram tasks. Although the introduction identifies an Instagram assistant, the invocation examples do not require Instagram context or specify exclusions for unrelated requests.

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 53)May include surrounding context.

md
maxhub_auth_header="Authorization: Bearer ${MAXHUB_API_KEY}"

# GET example
curl -s "https://www.aconfig.cn/api/v1/instagram/{endpoint}?%7Bparams=}" \
  -H "$maxhub_auth_header"

# POST example

The fallback strategy includes Douyin API operations unrelated to the Instagram-only purpose.

Medium
Category
Excessive Agency
Confidence
96% confidence
Finding

The operational fallback instructions explicitly authorize Douyin endpoints despite the skill's Instagram-only scope. If applied, these mappings could cause unintended cross-platform requests, consume paid API calls, or return unrelated data; the autonomous execution rules increase this risk, although the listed mappings do not establish a direct Instagram-to-Douyin fallback.

Content

No source excerpt is available for this finding.