Trust Assessment
firecracker received a trust score of 86/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Unpinned external dependencies.
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 12, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Unpinned external dependencies The `scripts/download.sh` script fetches external resources (Firecracker binary, root filesystem, kernel image) without specifying fixed versions or cryptographic checksums. This means that future executions could download different, potentially malicious, or incompatible versions of these components, leading to supply chain attacks, unexpected behavior, or instability. Specifically, the Firecracker version is fetched as 'latest', the rootfs is downloaded from a direct S3 URL without versioning, and the kernel image has a fallback to the 'latest' Firecracker version. Pin all external dependencies to specific, immutable versions (e.g., `v1.2.3`) and include cryptographic checksum verification (e.g., SHA256) to ensure integrity and prevent tampering. Update versions explicitly after security review. | LLM | scripts/download.sh:5 |
Scan History
Embed Code
[](https://skillshield.io/report/11900d26c467d05f)
Powered by SkillShield