Trust Assessment
gemini-stt received a trust score of 10/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 8 findings: 2 critical, 5 high, 1 medium, and 0 low severity. Key findings include Arbitrary command execution, Dangerous call: subprocess.run(), Suspicious import: urllib.request.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Static Code Analysis layer scored lowest at 33/100, 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 Findings8
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Arbitrary command execution Python shell execution (os.system, subprocess) Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands. | Manifest | skills/araa47/gemini-stt/transcribe.py:49 | |
| CRITICAL | Arbitrary command execution Python shell execution (os.system, subprocess) Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands. | Manifest | skills/araa47/gemini-stt/transcribe.py:72 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'get_gcloud_access_token'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/araa47/gemini-stt/transcribe.py:49 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'get_gcloud_project'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/araa47/gemini-stt/transcribe.py:72 | |
| HIGH | Potential data exfiltration: file read + network send Function 'transcribe_with_api_key' reads files and sends data over the network. This may indicate data exfiltration. Review this function to ensure file contents are not being sent to external servers. | Static | skills/araa47/gemini-stt/transcribe.py:87 | |
| HIGH | Potential data exfiltration: file read + network send Function 'transcribe_with_vertex' reads files and sends data over the network. This may indicate data exfiltration. Review this function to ensure file contents are not being sent to external servers. | Static | skills/araa47/gemini-stt/transcribe.py:120 | |
| HIGH | Arbitrary file content exfiltration via user-provided file path The skill accepts a user-provided `audio_file` path as input. It then reads the content of this file, base64 encodes it, and sends it to Google's Gemini or Vertex AI API for transcription. There is no validation to ensure that the provided path points to an actual audio file or that it is within an expected, restricted directory. A malicious actor could provide a path to any readable file on the system (e.g., `/etc/passwd`, `~/.ssh/id_rsa`, environment files, etc.), leading to the exfiltration of sensitive data to a third-party service (Google). 1. Implement robust validation for the `audio_file` path. This could include checking the file's magic bytes to confirm it's a known audio format, rather than relying solely on extension. 2. Restrict the allowed file paths to a specific, sandboxed directory (e.g., `~/.clawdbot/media/inbound/`) to limit the scope of accessible files. 3. Add a clear warning to the user about the security implications of providing arbitrary file paths. | LLM | transcribe.py:70 | |
| 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/araa47/gemini-stt/transcribe.py:26 |
Scan History
Embed Code
[](https://skillshield.io/report/7cfd4d2478f13b99)
Powered by SkillShield