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, Unsanitized user input directly embedded in LLM prompt.
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 | Unsanitized user input directly embedded in LLM prompt The `input` argument, which is directly controlled by the user via the CLI, is embedded without any sanitization or validation into the `userContent` string sent to the OpenAI API. An attacker can craft malicious input to manipulate the LLM's behavior, potentially overriding system instructions, extracting sensitive information (e.g., environment variables if the LLM is prompted to include them in the generated script), or generating harmful shell scripts. Implement robust input validation and sanitization for the `input` argument before it is used in the LLM prompt. Consider using techniques like strict allow-listing for expected values, escaping/encoding user input to prevent it from being interpreted as part of the prompt instructions, or instructing the LLM to ignore instructions within user input. | 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-script-gen/package.json |
Scan History
Embed Code
[](https://skillshield.io/report/5beb3ff2ac27fe75)
Powered by SkillShield