Trust Assessment
Rust Core Specialist 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 Agent instructed to execute shell script, Unpinned dependencies in build script.
The analysis covered 4 layers: manifest_analysis, llm_behavioral_safety, dependency_graph, static_code_analysis. All layers scored 70 or above, reflecting consistent security practices.
Last analyzed on February 12, 2026 (commit 78ae406e). 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 | Agent instructed to execute shell script The skill explicitly instructs the agent to use `scripts/init_project.sh`, which is a shell script containing `bash` commands. This grants the agent the capability to execute arbitrary shell commands on the host system. While the provided script is currently benign, this capability represents a significant security risk. An attacker could potentially modify the script or prompt the agent to execute other malicious commands, leading to command injection, data exfiltration, or system compromise. Re-evaluate the necessity of direct shell script execution. If unavoidable, ensure scripts are minimal, strictly controlled, and do not accept untrusted input. Consider sandboxing the execution environment or using a more constrained API for specific operations instead of direct shell access. | Unknown | SKILL.md:10 | |
| MEDIUM | Unpinned dependencies in build script The `scripts/init_project.sh` uses `cargo add` commands without specifying exact versions for dependencies (e.g., `tokio`, `anyhow`, `serde`). This means the latest available version will always be pulled. This introduces a supply chain risk, as new versions could introduce breaking changes, vulnerabilities, or even malicious code if a package maintainer's account is compromised or a package is hijacked. Without pinned versions, reproducibility and security auditing become more challenging. Pin all dependencies to specific versions (e.g., `cargo add tokio@1.x.x`). Regularly review and update dependencies to mitigate known vulnerabilities, but do so in a controlled manner after security checks. Consider using a dependency lock file (`Cargo.lock` is generated by `cargo build` or `cargo update`) and ensuring it's committed and respected. | Unknown | scripts/init_project.sh:9 |
Scan History
Embed Code
[](https://skillshield.io/report/7506535933f177bf)
Powered by SkillShield