Security audit

Copywriting Pro Skip

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only copywriting skill whose persuasive guidance is disclosed and aligned with its marketing purpose, though users should apply ethical judgment in sensitive contexts.

Install this if you want a strong marketing-copy assistant, but review outputs carefully for truthfulness, proportional urgency, and suitability for sensitive audiences such as health, finance, legal, or vulnerable consumers.

A.I.G

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

SkillSpector

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: 95% confidence
Finding: The skill description is activated by very broad phrases such as 'write, improve, rewrite, or review any marketing or sales copy,' which can cause the agent to select this skill for a wide range of generic writing tasks. Overbroad routing increases the chance that persuasive-sales tactics, behavioral nudges, or copy constraints are applied in contexts where they are inappropriate, leading to misalignment, policy bypass-by-context, or degraded handling of more suitable domain-specific skills.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The content explicitly instructs writers to 'deepen the wound' and 'sit in the agitation longer than feels comfortable,' which encourages deliberate amplification of fear, stress, and discomfort to drive action. In a copywriting skill, this is more dangerous than neutral educational discussion because it operationalizes manipulative persuasion tactics into user-facing outputs that can be used to exploit vulnerable audiences or pressure users into decisions against their interests.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 80% confidence
Finding: The document states that 'Most Americans read at a Grade 7 level' as the basis for a universal readability target. This embeds a specific national/locale assumption into the guidance without indicating that the rule is U.S.-only or that users can choose a different locale standard.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The checklist requires a 'Grade 6 reading level' via Hemingway Editor and prescribes specific word substitutions, which assumes an English-language writing standard. This is a natural-language policy concern because it enforces a locale/language-specific constraint without offering choice or explaining that the checklist is only for English copy.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.