Back to skill

Security audit

06 Marketing Promotion

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language community group-buying marketing reference skill with calculators and templates, and I found no hidden execution, credential access, persistence, or exfiltration behavior.

Installers should treat this as a Chinese-language marketing operations reference. Review generated promotion claims for legal and platform compliance, and add input validation before turning the included calculator snippets into production code.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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)

T09 · Insecure Skill Coding Practices

Note
Location
references/continuation.md:175
Finding

Unchecked numeric inputs allow division-by-zero denial of service

Content
View full analysis
Remediation
View remediation
None: if not isinstance(value, (int, float)) or not math.isfinite(value) or value <= 0: raise ValueError(f"{name} must be a finite number greater than zero") def require_nonnegative_integer(name: str, value: int) -> None: if not isinstance(value, int) or isinstance(value, bool) or value < 0: raise ValueError(f"{name} must be a nonnegative integer") require_positive_number("original_price", original_price) require_positive_number("duration_days", data.duration_days) require_nonnegative_integer("total_orders", data.total_orders) new_user_ratio = ( data.new_users / data.total_orders * 100 if data.total_orders > 0 else 0.0 ) ``` ]]>
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 (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

This markdown file includes a broad description of the skill's scope but does not define explicit trigger phrases, invocation boundaries, or negative examples clarifying when the skill should or should not activate. Without narrow activation guidance, an agent may invoke the skill for generic marketing-related requests beyond the intended community group-buying context.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

This markdown file embeds skill behavior and user-facing prompts entirely in Chinese, such as the printed title and input prompts for the ROI calculator. The policy requires flagging language or locale constraints when the skill forces a specific language without user opt-in, and no alternative language option or justification is provided in the surrounding text.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The tool description and generated copy templates are all Chinese-language outputs, and the run flow solicits input using Chinese prompts only. Because the skill dictates a single language for generated content without opt-in or a documented regional justification, it matches the natural-language policy violation criteria.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

This section defines a generator whose summaries, labels, and console output are all fixed in Chinese. There is no indication that the skill is region-specific or that users may opt into Chinese output, so the file imposes a language constraint contrary to the stated policy.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.