Back to skill

Security audit

LinkedIn Ads Copy Generator

Security checks for vulnerabilities and agentic risk

Overview

The skill provides a proportionate local drafting workflow, but its checks are incomplete and its optional Windows app needs separate review.

Manually verify 70-character fields and completed sections; a clean lint report does not guarantee compliant copy. Choose an output folder where replacing lint-report.md is acceptable. The optional Windows app is unnecessary for this workflow and requires its own security review; the supplied checksum alone does not establish safety.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The code implements only a partial draft linter, not the declared generation-and-linting workflow. Its hype-word checks align with the description, but generation and the distinct 70-character field check are absent. Local file reading and report writing are supporting implementation details, not unrelated capabilities.

Content

No source excerpt is available for this finding.

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: file_write.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

The linter enforces only a universal 150-character line limit, omitting the manifest's promised 70-character field validation.

Medium
Category
Excessive Agency
Confidence
99% confidence
Finding

The manifest promises linting for both 70- and 150-character fields, but MAX_CHARS is fixed at 150 (L086) and applied uniformly to every line without identifying fields. Consequently, a headline exceeding 70 characters but fitting within the universal limit can pass without a length warning.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.