Trust Assessment
backup-script-gen received a trust score of 65/100, 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, 0 high, 1 medium, and 0 low severity. Key findings include Unpinned npm dependency version, Direct User Input in LLM Prompt (Prompt 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 | Direct User Input in LLM Prompt (Prompt Injection) The user-provided input (`spec`) is directly interpolated into the `userContent` message sent to the OpenAI LLM without any sanitization or separation. This allows for classic prompt injection attacks where a malicious user could craft the input to manipulate the LLM's behavior, override the system prompt, or attempt to extract sensitive information from the LLM's context. Given that the LLM is instructed to generate shell scripts, a successful prompt injection could lead to the generation of malicious or unintended commands. Implement robust prompt engineering techniques to isolate user input from system instructions. Consider using structured input, dedicated input fields, or a separate LLM call to validate/sanitize user input before incorporating it into the main prompt. Alternatively, use techniques like XML/JSON tags to clearly delineate user input within the prompt, making it harder for the LLM to misinterpret user input as instructions. Example: `Generate a backup script for the following user request: <user_request>${input}</user_request>`. | LLM | src/index.ts:8 | |
| MEDIUM | Unpinned npm dependency version Dependency 'commander' is not pinned to an exact version ('^12.1.0'). Pin dependencies to exact versions to reduce drift and supply-chain risk. | Dependencies | skills/lxgicstudios/backup-gen/package.json |
Scan History
Embed Code
[](https://skillshield.io/report/a731179218acbf0d)
Powered by SkillShield