merge-split-av-streams-desktop

Pass

Audited by Gen Agent Trust Hub on Aug 30, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill serves as a developer guide for integrating split media streams. The provided Kotlin code implements a custom URL protocol (edl://) used by established media players like mpv.- [COMMAND_EXECUTION]: The skill includes bash snippets using grep for local repository auditing. These commands are static, diagnostic in nature, and intended for the user to verify their own implementation rather than for autonomous agent execution.- [DATA_EXPOSURE]: No sensitive file paths, environment variables, or hardcoded credentials were found. The URL handling is localized to the media engine's internal representation.- [PROMPT_INJECTION]: The content is strictly technical and instructional. It contains no instructions directed at overriding the agent's behavior or safety filters.- [INDIRECT_PROMPT_INJECTION]: While the skill describes processing external stream URLs, it explicitly details sanitization via length-prefixed quoting (e.g., %len%value) to ensure data is treated as a literal value by the downstream media engine, mitigating protocol injection risks.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 30, 2026, 07:03 AM
Security Audit — agent-trust-hub — merge-split-av-streams-desktop