Trust Assessment
rsdoctor-analysis received a trust score of 83/100, 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 Potential Command Injection via unsanitized file paths, Unpinned dependency installation for `@rsdoctor/agent-cli`.
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 June 1, 2026 (commit 76880945). 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 | Potential Command Injection via unsanitized file paths The skill instructs the agent to locate `rsdoctor-data.json` from user-provided paths or by searching the filesystem. This path is then used with `rsdoctor-agent` and potentially `rg`. If the agent constructs shell commands by directly interpolating these paths without proper sanitization (e.g., quoting), a malicious path like `foo.json; rm -rf /` could lead to arbitrary command execution on the host system. Instruct the agent to always sanitize or properly quote any user-provided or dynamically discovered file paths before incorporating them into shell commands. For example, use `shlex.quote()` in Python or similar mechanisms in other languages. | LLM | SKILL.md:25 | |
| MEDIUM | Unpinned dependency installation for `@rsdoctor/agent-cli` The skill instructs the agent to "install latest only if missing/outdated" for the `@rsdoctor/agent-cli` package. Installing the latest version without specifying a pinned version (e.g., `npm install @rsdoctor/agent-cli@1.2.3`) introduces a supply chain risk. If a malicious version of the package is published, the agent could install and execute it, leading to compromise of the host system or data exfiltration. Instruct the agent to install `@rsdoctor/agent-cli` with a pinned version (e.g., `npm install @rsdoctor/agent-cli@<specific-version>`) or at least a major/minor version range (e.g., `npm install @rsdoctor/agent-cli@^1.0.0`) to mitigate the risk of installing a malicious or breaking update. The skill could also specify a minimum trusted version. | LLM | SKILL.md:30 |
Scan History
Embed Code
[](https://skillshield.io/report/8b9ffc7f305f9ae9)
Powered by SkillShield