ffmpeg-usage
Fail
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: HIGHREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The
README.mdandinstall.shfiles promote a 'Quick Install' method that fetches a script from GitHub and pipes it directly into the shell usingcurl -sSL https://raw.githubusercontent.com/ychoi-kr/claude-ffmpeg-skill/main/install.sh | bash. This pattern allows for the execution of arbitrary remote code on the user's host machine. - [COMMAND_EXECUTION]: The skill is primarily designed to facilitate shell command execution.
- The
validate.pyscript executes multipleffmpegandffprobecommands via Python'ssubprocess.runto check the environment. - The
examples/conversion.shscript is an interactive shell script that prompts for file paths and executesffmpegcommands based on that input. - [EXTERNAL_DOWNLOADS]: The
install.shscript performs agit clonefromhttps://github.com/ychoi-kr/claude-ffmpeg-skill.gitto install the skill files into the user's home directory (~/.claude/skills). - [DATA_EXFILTRATION]: The
validate.pyscript collects system information, including Operating System type, release, architecture, and Python version, and saves this data to a local file namedvalidation_report.json. While intended for troubleshooting, this represents unauthorized collection of host environment metadata. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to the way it handles external data.
- Ingestion points: User-provided filenames, durations, and timestamps are interpolated into shell commands (found in
SKILL.md). - Boundary markers: Absent. The skill does not instruct the agent to use delimiters or ignore embedded instructions when processing user-provided paths.
- Capability inventory: The skill provides instructions for executing complex shell commands with
ffmpeg, including the-safe 0flag for concatenation, which disables safety checks for file paths. - Sanitization: Absent. There are no specific instructions for the agent to sanitize shell metacharacters or validate paths against directory traversal before executing the generated commands.
Recommendations
- HIGH: Downloads and executes remote code from: https://raw.githubusercontent.com/ychoi-kr/claude-ffmpeg-skill/main/install.sh - DO NOT USE without thorough review
Audit Metadata