Trust Assessment
jules-api received a trust score of 56/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 2 findings: 1 critical, 1 high, 0 medium, and 0 low severity. Key findings include Arbitrary command execution, Unsanitized user input in curl URL path leads to argument injection.
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 Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Arbitrary command execution Node.js synchronous shell execution 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/sanjacob99/jules-and-lobster/scripts/jules.js:17 | |
| HIGH | Unsanitized user input in curl URL path leads to argument injection The `jules_api.sh` script constructs `curl` commands where the `session_id` variable is directly interpolated into the URL path. The `session_id` is taken directly from user input without validation or sanitization. If `session_id` contains a string starting with a hyphen (e.g., `--output /tmp/malicious.txt`), `curl` will interpret this as a command-line option rather than part of the URL. This allows an attacker to inject arbitrary `curl` arguments, potentially leading to arbitrary file writes, data exfiltration, or other malicious actions. Implement strict validation for `session_id` to ensure it only contains expected characters (e.g., alphanumeric, no hyphens or special characters that could be interpreted as `curl` options). For `session_id`, a simple regex validation for an expected ID format would be the most effective solution. | LLM | scripts/jules_api.sh:70 |
Scan History
Embed Code
[](https://skillshield.io/report/b0997e90129698e4)
Powered by SkillShield