Trust Assessment
rsbuild-v2-upgrade received a trust score of 78/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 2 findings: 0 critical, 1 high, 1 medium, and 0 low severity. Key findings include Direct shell command execution via npx, Unpinned dependency update via npx taze.
The analysis covered 4 layers: manifest_analysis, llm_behavioral_safety, static_code_analysis, dependency_graph. All layers scored 70 or above, reflecting consistent security practices.
Last analyzed on February 11, 2026 (commit 46637d3c). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Direct shell command execution via npx The skill's workflow explicitly instructs the agent to execute a shell command: `npx taze major --include /rsbuild/ -w -r`. If the AI agent is designed to directly execute shell commands found within its skill definitions without proper sandboxing, user confirmation, or validation, this constitutes a command injection vulnerability. An attacker could potentially modify the skill content to execute arbitrary commands on the host system. The agent should be designed to prompt for user confirmation before executing any shell commands, or execute them within a strictly sandboxed environment with minimal permissions. Alternatively, the skill could be rephrased to suggest the command for the user to run manually, rather than implying agent execution. | Unknown | SKILL.md:19 | |
| MEDIUM | Unpinned dependency update via npx taze The skill uses `npx taze major` to update dependencies. `npx` by default fetches and executes the latest version of the `taze` package, and `taze major` then updates all specified packages (those matching `/rsbuild/`) to their latest major versions. This introduces a supply chain risk because it relies on the integrity of the `taze` package and all `@rsbuild` packages at the time of execution. A compromise in any of these packages could lead to malicious code being introduced into the user's project without explicit version pinning or review. To mitigate this supply chain risk, consider pinning the `taze` package to a specific version (e.g., `npx taze@x.y.z`) or using a package manager's update command that respects lockfiles and allows for more controlled updates. For `@rsbuild` packages, advise users to carefully review major version changes and their implications before applying them. | Unknown | SKILL.md:19 |
Scan History
Embed Code
[](https://skillshield.io/report/0504661890a922fe)
Powered by SkillShield