Back to skill

Security audit

Video

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward local video-processing guide with expected FFmpeg and optional local transcription workflows, and no evidence of hidden behavior or unsafe persistence.

Installers should understand that this skill will guide an agent to process local media files and create derived outputs. Use it on files you are authorized to edit or transcribe, choose unique output names, and avoid processing confidential recordings unless local handling and retention are acceptable.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The workflow explicitly transcribes audio content with Whisper but provides no privacy, consent, or sensitive-data handling guidance. In a video-processing skill, this can lead users to process recordings containing personal, confidential, or regulated spoken content without realizing the legal and privacy implications, especially for meetings, classrooms, interviews, or client material.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

This markdown file provides many ffmpeg commands that write new output files, but it does not include any warning that running these commands will create or replace files on disk. Because SQP-2 applies to markdown files when descriptions omit warnings about behaviors affecting user data or system integrity, the lack of any caution about output-path handling is a minor safety disclosure gap.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

Line L042 states "Always use AAC for maximum compatibility," which is a natural-language instruction forcing a specific technical choice without presenting it as conditional guidance or offering alternatives. Under the policy rule, absolute language that imposes a fixed option without user opt-in or clear scope can be considered a policy-style constraint violation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.