Trust Assessment
skill-audit received a trust score of 80/100, 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 Skill allows reading arbitrary local files via user-controlled path, Unpinned dependencies introduce supply chain risk.
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 Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Skill allows reading arbitrary local files via user-controlled path The `/register-skill <path>` command is described as reading `skill.md` at the given path. If the `<path>` argument is not strictly validated or sandboxed by the runtime environment, an attacker could provide a path to sensitive local files (e.g., `/etc/passwd`, `~/.ssh/id_rsa`, environment files) leading to data exfiltration. This represents an excessive permission that could be exploited. Implement strict path validation to ensure only allowed `skill.md` files within a designated, sandboxed directory can be read. Avoid allowing arbitrary file system access. The skill's runtime environment should also enforce sandboxing to limit file system access. | LLM | skill.md:10 | |
| MEDIUM | Unpinned dependencies introduce supply chain risk The skill's implementation uses `require('@rocketlabs/skill-audit')` without specifying an exact version. Additionally, the prerequisites list `@solana/web3.js v1.x` and `@iqlabs-official/solana-sdk v0.1.1+`, which are broadly versioned. Unpinned or broadly versioned dependencies can lead to unexpected behavior, security vulnerabilities, or breaking changes if a new version introduces malicious code or regressions. This makes the skill vulnerable to supply chain attacks if a dependency is compromised or updated with breaking changes. Pin all dependencies to exact versions (e.g., `1.2.3`) to ensure deterministic builds and prevent unexpected updates. Use a lock file (e.g., `package-lock.json`, `yarn.lock`) to manage transitive dependencies and ensure consistent installations across environments. | LLM | skill.md:40 |
Scan History
Embed Code
[](https://skillshield.io/report/148ffcc02d2bb4c2)
Powered by SkillShield