Ai Powered Content Repurposing

• Outcome: Review
• Latest audit: Sep 15, 2026 · 1:44 AM UTC
• Version: 1.0.0

Overview

The skill is a content-repurposing guide, but it advertises broad publishing, syncing, and third-party integrations without clear implementation details, data-sharing disclosure, or confirmation boundaries.

Review this skill carefully before installing. It is not malicious code, but treat any publishing, CRM sync, Google Drive import, WordPress access, Slack webhook use, or social distribution as sensitive. Only provide credentials you intend to use, avoid confidential or regulated source material unless approved, and require manual review before anything is posted or synced externally.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection

Findings (7)

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"],

Anti-Refusal Statement

High

• Category: Anti-Refusal
• Confidence: 80% confidence

Finding

Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.

Content

Scanner excerpt · SKILL.md (reported line 302)May include surrounding context.

md

⚠️ LIMITATIONS
- Requires human editing for factual claims
- Inconsistent voice across batches without guardrails
- May duplicate common marketing clichés

✅ RECOMMENDATION

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 82% confidence

Finding

The description says to use the skill when the user needs "content automation, multi-channel distribution, or quick content recycling," which is a wide, natural-language trigger without clear boundaries. It does not define specific trigger phrases, scope limits, or negative examples to distinguish this skill from ordinary writing or marketing-assistance requests.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium

• Category: Not specified by scanner
• Confidence: 88% confidence

Finding

The documentation promotes multiple third-party integrations and content distribution paths without a clear, prominent warning that user content may be sent to external providers. In a content-repurposing context, source material may include unpublished marketing plans, proprietary drafts, client data, or regulated information, so the lack of disclosure raises meaningful privacy and confidentiality risk.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium

• Category: Not specified by scanner
• Confidence: 93% confidence

Finding

The skill claims automated integrations with WordPress, Google Drive, Slack, LinkedIn, Twitter, Instagram, HubSpot, Medium, Substack, and Ghost, but no implementation is present to substantiate those behaviors or constraints. Misrepresenting external integration capability can mislead users into assuming validated automation, safe handling, or controlled publishing flows where none exist, increasing the chance of unsafe manual workarounds or unintended data sharing.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium

• Category: Not specified by scanner
• Confidence: 92% confidence

Finding

The 'What This Skill WILL Do' section makes concrete assurances such as maintaining factual accuracy and optimizing content, despite there being no implementation in the audited file to enforce those guarantees. Overstated safety or quality guarantees can cause users to overtrust outputs and skip verification, especially for regulated or reputationally sensitive content.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Low

• Category: Not specified by scanner
• Confidence: 79% confidence

Finding

The manifest metadata requires OPENAI_API_KEY and ANTHROPIC_API_KEY, which is a credential-access capability. While AI model usage is thematically related to content repurposing, this file contains only documentation and no actual executable implementation showing those keys are needed here, so the capability is unjustified by the concrete artifact being audited.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.