Back to skill

Security audit

Generate Micro-Moment Copy with AI — Instant Marketing Content

Security checks for vulnerabilities and agentic risk

Overview

This is a prompt-only marketing copy skill with some compliance overclaims, but no hidden execution, persistence, or data exfiltration behavior was found.

Installers should treat this as a copywriting aid, not a compliance checker. Review all generated claims, scarcity, urgency, social proof, and privacy-sensitive targeting before publishing, and provide only the customer or analytics data needed for the requested copy.

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 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 7)May include surrounding context.

md
{"openclaw":{"requires":{"env":["OPENAI_API_KEY","ANTHROPIC_API_KEY"],"bins":["jq"]},"os":["macos","linux","win32"],"files":["SKILL.md"],"emoji":"✍️"}}

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill claims it 'validates' honesty, factual accuracy, and privacy-law compliance, but the file contains only descriptive guidance and prompt-based behavior with no enforceable validation mechanism. This can create misplaced operator trust, leading users to rely on the skill for compliance-sensitive marketing copy when deceptive, noncompliant, or privacy-invasive content may still be generated.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The configuration sets the language parameter to "en" by default, which imposes a specific language choice in the skill interface. The file does not present this default as an explicit user opt-in at that point, so it may conflict with language/locale policy expectations.

Content

No source excerpt is available for this finding.