musia-lalachan-mv-workflow

Pass

Audited by Gen Agent Trust Hub on Oct 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes local shell scripts (scripts/mux_musia_audio.sh, scripts/wait_downloaded_mp4.sh) to perform media operations. These scripts execute system binaries including ffmpeg for audio/video muxing and find/stat for monitoring the ~/Downloads directory. The scripts handle arguments with standard shell quoting to mitigate simple command injection.
  • [INDIRECT_PROMPT_INJECTION]: The workflow involves generating prompts for the Xiaoyunque AI agent based on data ingested from local creative project files, such as STORY.md and ASSET_LIST.md located in the SKILL.md defined directories.
  • Ingestion points: Project metadata and content located in $MUSIA_ROOT/data/creative_projects/ are used to build storyboards and prompts.
  • Boundary markers: The skill lacks explicit instructions for the agent to sanitize or escape song titles or story content before they are interpolated into the generated Xiaoyunque prompts.
  • Capability inventory: The skill possesses the ability to execute shell commands via ffmpeg and ffprobe, and perform file-write operations within project directories.
  • Sanitization: While the skill provides explicit instructions to avoid including local filesystem paths in prompts (preferring asset labels like 图1), it does not specify sanitization for user-generated text fields that form the core of the story and visual instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 19, 2026, 06:48 PM