Back to skill

Security audit

Analyze Content Narrative Arc with AI — Structure & Flow Detection

Security checks for vulnerabilities and agentic risk

Overview

This skill is a Markdown-only content analysis helper with disclosed OpenAI API use and no executable install, persistence, or hidden local authority.

Installers should be comfortable sharing pasted drafts or transcripts with the configured AI provider, especially for confidential or unpublished business content. Treat generated rewrites as suggestions requiring human review before publication.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 14)May include surrounding context.

md
"files": ["SKILL.md"],

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill is presented as an analysis tool, but its documented behavior includes drafting replacement copy and stronger openings. This mismatch can cause users or downstream systems to treat it as low-risk analysis-only processing while it is in fact generating persuasive content, which changes trust, review, and safety expectations.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill advertises integrations and requires an API key, but it does not clearly warn that pasted content may be transmitted to external services for processing. Because this skill is meant for long-form articles, scripts, whitepapers, and email sequences, users may submit confidential or unpublished material, creating a real privacy and data-handling risk.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The safety section claims the skill does not generate original content, yet earlier sections promise rewrites and alternative hooks. Contradictory safety claims can mislead users, auditors, or policy engines into underestimating the model's generative behavior, increasing the chance of unreviewed output being trusted or published.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The limitation says the skill's narrative advice is optimized for Western narrative conventions, which imposes a cultural/locale bias in the skill's behavior. Because the file does not present this as an opt-in mode or offer alternative frameworks, it may conflict with the policy against forcing a specific locale or cultural convention without user choice.

Content

No source excerpt is available for this finding.