Trust Assessment
gettr-transcribe-summarize received a trust score of 58/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 6 findings: 3 critical, 1 high, 2 medium, and 0 low severity. Key findings include Suspicious import: urllib.request, Command Injection via untrusted URL in download_audio.sh, Command Injection in run_pipeline.sh via video URL.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The LLM Behavioral Safety layer scored lowest at 0/100, indicating areas for improvement.
Last analyzed on February 13, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings6
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Command Injection via untrusted URL in download_audio.sh The `download_audio.sh` script directly uses the `$IN_URL` variable in an `ffmpeg` command without proper sanitization or quoting. If `$IN_URL` contains shell metacharacters (e.g., `'; rm -rf /'`), an attacker could inject arbitrary commands, leading to remote code execution. Sanitize or strictly validate the `$IN_URL` variable to ensure it contains only a valid URL. Alternatively, use a more robust method for calling `ffmpeg` from a Python script using `subprocess.run` with `shell=False` and passing arguments as a list, which prevents shell interpretation. | LLM | scripts/download_audio.sh:19 | |
| CRITICAL | Command Injection in run_pipeline.sh via video URL The `run_pipeline.sh` script passes the user-controlled `$VIDEO_URL` directly to `download_audio.sh`. Since `download_audio.sh` is vulnerable to command injection via its URL argument, this propagates the vulnerability, allowing an attacker to execute arbitrary commands by crafting a malicious `VIDEO_URL`. Address the underlying command injection vulnerability in `scripts/download_audio.sh`. Ensure all user-provided inputs are properly sanitized or validated before being used in shell commands. | LLM | scripts/run_pipeline.sh:79 | |
| CRITICAL | Command Injection in run_pipeline.sh via language flag The `run_pipeline.sh` script constructs the `$LANG_FLAG` variable from user-provided `$LANGUAGE` input and then directly interpolates it into the `mlx_whisper` command. If `$LANGUAGE` contains shell metacharacters (e.g., `'; rm -rf /'`), an attacker could inject arbitrary commands, leading to remote code execution. Strictly validate the `$LANGUAGE` variable against a whitelist of known language codes. Alternatively, construct the command arguments as an array and execute with `bash -c` or a similar method that prevents shell interpretation of individual arguments. | LLM | scripts/run_pipeline.sh:105 | |
| HIGH | Unpinned dependency: mlx-whisper The `mlx-whisper` package is installed via `pip` without a pinned version. This introduces a supply chain risk, as a malicious update to the package could be automatically installed, compromising the skill's integrity and security. Pin the version of `mlx-whisper` in the manifest (e.g., `"package": "mlx-whisper==X.Y.Z"`) to ensure deterministic and secure installations. | LLM | SKILL.md | |
| MEDIUM | Suspicious import: urllib.request Import of 'urllib.request' detected. This module provides network or low-level system access. Verify this import is necessary. Network and system modules in skill code may indicate data exfiltration. | Static | skills/kevin37li/gettr-transcribe-summarize/scripts/extract_gettr_og_video.py:28 | |
| MEDIUM | Unpinned dependency: ffmpeg The `ffmpeg` package is installed via `brew` without a pinned version. While `brew` is generally more curated than `pip`, relying on the latest version can still introduce breaking changes or, in rare cases, security vulnerabilities if a compromised version is pushed to the repository. While direct version pinning for `brew` is less common, consider documenting the recommended `ffmpeg` version or using a specific `brew` tap if a stable, pinned version is critical for security and stability. | LLM | SKILL.md |
Scan History
Embed Code
[](https://skillshield.io/report/5d861fe71a62b828)
Powered by SkillShield