Trust Assessment
openai-whisper received a trust score of 76/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 1 finding: 1 critical, 0 high, 0 medium, and 0 low severity. Key findings include Potential Command Injection via `whisper` CLI arguments.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. All layers scored 70 or above, reflecting consistent security practices.
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 Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Potential Command Injection via `whisper` CLI arguments The skill is designed to execute the `whisper` command-line interface, as indicated by the manifest's `requires` field (`"bins": ["whisper"]`). The untrusted `SKILL.md` provides examples of `whisper` usage, including arguments like file paths (`/path/audio.mp3`), output directories (`--output_dir .`), and other options (`--model`, `--output_format`, `--task`). If the skill constructs the `whisper` command string using unsanitized user input for these arguments, it could lead to arbitrary command execution. An attacker could inject malicious shell commands by crafting a specially formed input (e.g., a file path like `"; rm -rf /; #.mp3"`). Ensure all user-provided inputs used to construct the `whisper` command are thoroughly sanitized and validated. Prefer using `subprocess.run` with `shell=False` and passing arguments as a list to prevent shell injection. Restrict the output directory to a safe, temporary location if possible, and validate all file paths. | LLM | SKILL.md:6 |
Scan History
Embed Code
[](https://skillshield.io/report/56acac8baffa4998)
Powered by SkillShield