Security audit

Video Repurposing Script Generator

Security checks for vulnerabilities and agentic risk

Overview

The skill is not clearly malicious, but it advertises API-connected posting, scheduling, and content distribution without enough scoping, consent, or privacy detail.

Review this skill carefully before installing. Use it only for videos you are authorized to process, avoid confidential or regulated recordings unless you have approved external transcription, pin dependencies in an isolated environment, and do not configure Buffer, HubSpot, WordPress, Slack, Zapier, or similar credentials unless you are comfortable with the agent potentially preparing or performing outbound publishing workflows under explicit user control.

A.I.G

Vulnerability Patterns

Insecure DependenciesIntroduces malicious components through unsafe dependency sources
Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Findings (2)

T08 · Insecure Dependencies

Warning

Location: SKILL.md:152
Finding: Unpinned Third-Party Dependencies Create a Supply-Chain Execution Risk
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Warning

Location: SKILL.md:59
Finding: Sensitive Video Content May Be Transmitted to an External Transcription Provider Before Privacy Review
Content: View full analysis
Remediation: View remediation

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 (6)

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","YOUTUBE_API_KEY"],"bins":["ffmpeg"]},"os":["macos","linux","win32"],"files":["SKILL.md"],"emoji":"🎬"}}

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The manifest description says to use the skill when a user needs to 'repurpose video content,' 'maximize reach across platforms,' or 'automate social media posting.' These are broad, generic intents without clear trigger boundaries or exclusions, which could cause unintended invocation for ordinary marketing requests.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The skill is presented primarily as a script-generation tool, but the documentation also advertises integrations for publishing, scheduling, notification, and distribution. This expands the effective trust boundary and can mislead users into providing credentials or content under the assumption that the skill is limited to drafting, increasing the risk of unintended data sharing or downstream actions.
Content: No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: Claiming direct publishing or distribution capabilities without clearly justifying or constraining them creates a scope-creep risk: users may grant API keys or authorize workflows that can post, notify, or distribute content beyond expected behavior. Even if not implemented here, the documentation normalizes higher-privilege behavior and can lead to unsafe deployment patterns.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The skill references integrations that can distribute content or share data with third parties, but it does not clearly explain downstream publishing, credential use, or data-sharing implications. In a workflow involving video transcripts, metadata, and marketing copy, that omission can cause users to expose sensitive business content or authorize actions they did not fully anticipate.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The safety section says the skill will not create deceptive hooks or clickbait, but earlier sections promote trend-jacking, engagement optimization, and reply-baiting tactics. This contradiction weakens trust in the guardrails and may encourage manipulative content generation under a veneer of safety, leading to policy violations or reputational harm.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.