Security audit

news-video-maker

Security checks for vulnerabilities and agentic risk

Overview

This skill has a coherent news-video purpose, but its FFmpeg command pattern can expose users to unsafe local command execution if file paths are not tightly controlled.

Install only if you are comfortable with a skill that searches the web, sends text to a TTS tool, creates local media files, and invokes FFmpeg. Use trusted local file paths and output directories, and prefer an implementation that runs FFmpeg with a fixed argument array plus strict path and subtitle-filter escaping rather than pasting interpolated paths into a shell command.

A.I.G

Vulnerability Patterns

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
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally

Findings (1)

T09 · Insecure Skill Coding Practices

Error

Location: SKILL.md:45
Finding: Shell Command Injection Through Unsafely Interpolated File Paths
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The skill description is broad enough that it could be invoked for loosely related requests about news, video creation, or summaries without clear boundaries. Over-broad activation increases the chance the agent performs external searches and file-generating actions unexpectedly, which can surprise users and expand exposure to untrusted content.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The skill instructs the agent to fetch external news, generate speech, and write media files via FFmpeg, but it does not warn users about data flow to external tools, untrusted search content, or filesystem side effects. In this context, the combination of web retrieval plus local file creation is more dangerous because untrusted text and file paths may be passed into downstream tooling without explicit user awareness or confirmation.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The example prompt is very generic and overlaps with ordinary requests for news summaries. This can cause accidental invocation of a skill that performs external search, synthesis, and media generation when the user may only want informational output, increasing the risk of unintended actions and processing of untrusted data.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.