Security audit

Al Content Repurposer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent content-repurposing workflow with disclosed batch, remote-source, and scheduling features, and I found no artifact-backed malicious behavior.

Before installing, confirm whether you actually want scheduled runs, RSS watching, or any publishing integration enabled. Use trusted source URLs, review generated drafts before publishing, and verify dependencies because the referenced requirements and scripts are not included in this artifact.

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

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands

Findings (8)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 85% confidence
Finding: The README promotes unattended batch processing, scheduling, and RSS/feed-driven automation while emphasizing that outputs are automatically written to organized folders, but it does not warn users about the risks of mass file generation, accidental overwrites, or autonomous operation on unreviewed inputs. In a content-generation skill, this can lead to silent production of large volumes of AI-generated material, propagation of low-quality or harmful content, and operational surprises when run on a schedule.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The manifest frames the skill as content repurposing, but the documentation adds scheduling and broader workflow automation capabilities. This mismatch can cause operators or policy systems to grant the skill more trust or permissions than intended, increasing the risk of unauthorized recurring actions or unexpected outbound activity.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The skill accepts remote URLs, YouTube links, podcast RSS feeds, and WordPress sources without warning about privacy, data handling, or the implications of fetching third-party content. In practice, this can expose user IPs or infrastructure to external services, pull sensitive or copyrighted material into processing pipelines, and create compliance issues if operators assume only local content is handled.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The documented behavior expands from repurposing a provided item to continuously watching RSS feeds and ingesting remote content on a schedule. That materially changes the trust model by introducing unattended network retrieval and ongoing processing, which can lead to data exposure, unintended scraping, or repeated interaction with external systems.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The directory structure documents an auto-post publishing script even though the skill is described as generation-focused. Undisclosed publishing functionality is more dangerous than mere content transformation because it can trigger outbound actions on third-party platforms, potentially causing account abuse, reputational damage, or accidental disclosure.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The template enables auto-scheduling with no visible confirmation or warning, which can cause generated content to be published automatically without an explicit final user approval step. In a content-repurposing skill, this increases the risk of unintended disclosure, brand damage, or publication of inaccurate or sensitive material at scale.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 86% confidence
Finding: The configuration sets default_language: "en", which establishes an English-only default behavior in natural-language processing. Because the file does not indicate any user-selectable language option or justification for this locale constraint, it may conflict with language/locale choice policy expectations.
Content: No source excerpt is available for this finding.

Vague Triggers

Low

Category: Not specified by scanner
Confidence: 85% confidence
Finding: This is a manifest file, so vague-trigger checks apply. The description "Standard Twitter thread format: hook → numbered tweets → CTA" describes a very generic writing pattern without any scope, audience, or exclusion criteria, which can make invocation or template selection ambiguous when multiple content-writing skills exist.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.