Trust Assessment
cookidoo received a trust score of 85/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 3 findings: 0 critical, 0 high, 2 medium, and 1 low severity. Key findings include Suspicious import: urllib.request, Insecure storage of Cookidoo session cookies and refresh token, Missing input validation for recipe_id in API calls.
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 Findings3
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| 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/lars147/tmx-cli/tmx_cli.py:21 | |
| MEDIUM | Insecure storage of Cookidoo session cookies and refresh token The `tmx_cli.py` script stores sensitive user session cookies and a refresh token in `cookidoo_cookies.json` directly within the skill's script directory (`SCRIPT_DIR`). This location is generally less secure than a dedicated user-specific configuration directory (e.g., `~/.config/tmx-cli/`) and could expose credentials if the skill's deployment directory is compromised or has overly broad read permissions for other processes or users on the system. This poses a risk of credential harvesting or data exfiltration if the file is accessed by unauthorized entities. Store `cookidoo_cookies.json` in a user-specific, protected configuration directory, such as `Path.home() / ".config" / "tmx-cli" / "cookies.json"`, similar to how `CONFIG_FILE` is handled. Ensure appropriate file permissions are set (e.g., `0o600`) to restrict access. | LLM | tmx_cli.py:30 | |
| LOW | Missing input validation for recipe_id in API calls The `recipe_id` argument, which can be user-controlled, is directly interpolated into various API endpoint URLs (e.g., `/api/v2/recipes/{recipe_id}`). There is no explicit validation to ensure `recipe_id` conforms to an expected format (e.g., integer, UUID) before being used in the URL. While the Cookidoo API is likely to reject malformed IDs, a crafted `recipe_id` could potentially lead to unexpected behavior or, in a highly theoretical scenario, contribute to a Server-Side Request Forgery (SSRF) if the API gateway or backend has specific vulnerabilities related to path parsing or redirects. This is a general best practice for robust input handling. Implement strict validation for `recipe_id` arguments to ensure they match the expected format (e.g., a numeric ID or UUID pattern) before constructing API URLs. This can be done using regular expressions or type checks in the argument parsing or function calls. | LLM | tmx_cli.py:400 |
Scan History
Embed Code
[](https://skillshield.io/report/9b5ede93e80d2f96)
Powered by SkillShield