Back to skill

Security audit

自动化营销推广师

Security checks for vulnerabilities and agentic risk

Overview

This skill is openly designed to automatically monitor social platforms and post promotional replies, which creates account, spam, privacy, and reputation risk without clear human approval controls.

Install only if you intentionally want an automated marketing agent and can constrain it. Require human approval before any post or private message, use platform-compliant credentials with minimum scopes, add rate limits and audit logs, and define what monitored content and reply metadata may be stored and for how long.

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
Findings (1)

T01 · Skill Instruction Hijacking

Error
Location
SKILL.md:27
Finding

Mandatory Promotional Output Injection and Automated Distribution

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
78% confidence
Finding

The natural-language instructions and examples are entirely in Chinese and present the skill as operating in that language, but do not offer any user language/locale selection. Under the policy, forcing a specific language without opt-in can be a locale-policy violation unless clearly justified as region-specific.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly describes fully automated monitoring, reply generation, and posting across public platforms and private messaging channels without any user-facing warning, approval gate, or platform-safety constraints. This is dangerous because it enables unattended mass outreach, spam, impersonation-like behavior, and accidental policy violations that can cause reputational, legal, and account-enforcement harm.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill continuously monitors third-party content every 15 minutes and records reply metadata, but it provides no privacy or data-handling disclosure, retention policy, or consent/authorization boundaries. This is dangerous because it normalizes collection and storage of user-generated content and interaction data without clear limits, increasing the risk of privacy violations, unlawful scraping, and misuse of personal data.

Content

No source excerpt is available for this finding.