Security audit
Security checks for vulnerabilities and agentic risk
This skill locally combines MP3 files into MP4 playlist videos and does not show hidden, persistent, network, credential, or destructive behavior.
Use this skill only on media files you intend to process, and choose output/temp paths carefully because ffmpeg may overwrite existing files. Expect local CPU/disk use and local timeline files containing playlist filenames; no network or credential access was found.
The skill advertises substantially richer behavior than the analysis indicates is actually implemented. This kind of description-behavior mismatch is dangerous because users or orchestration layers may trust the declared capabilities, skip validation, or make decisions based on nonexistent checks and rendering steps, which can lead to unsafe automation assumptions and incorrect execution paths.
The skill instructs the agent to run shell commands and write files, but it does not declare any explicit tool scope such as allowed-tools or permissions. That makes the skill's operational boundary ambiguous and can let an agent invoke broader shell/file capabilities than reviewers or users expect, increasing the chance of unintended command execution or filesystem modification.
The manifest description and usage guidance are written entirely in Chinese, and the trigger list mixes Chinese and English without stating that language choice is optional. For a general-purpose media-processing skill, this creates an implicit language/locale constraint without documenting user choice or a region-specific justification.
Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.
brew install ffmpeg
sudo apt install ffmpeg
### 输出视频时长为 0
subprocess module calls execute external commands. Without careful input validation, this enables command injection.
def run_command(cmd, label, cwd=None):
try:
return subprocess.run(cmd, check=True, capture_output=True, text=True, cwd=cwd)
except FileNotFoundError as exc:
raise RuntimeError(f"{label} 未找到: {cmd[0]}") from exc
except subprocess.CalledProcessError as exc:
subprocess module calls execute external commands. Without careful input validation, this enables command injection.
def run_command(cmd, label):
try:
return subprocess.run(cmd, check=True, capture_output=True, text=True)
except FileNotFoundError as exc:
raise RuntimeError(f"{label} 未找到: {cmd[0]}") from exc
except subprocess.CalledProcessError as exc:
This file contains user-facing docstrings, status messages, errors, and argument help text entirely in Chinese, which imposes a specific language on users. Under the stated policy, forcing a language without user opt-in is a natural-language policy violation unless the locale constraint is explicitly justified or configurable.
This code file contains natural-language strings entirely in Chinese, including the module docstring, runtime messages, and CLI help text. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is explicitly justified, which is not present here.
No suspicious patterns detected.