Trust Assessment
share_usecase received a trust score of 70/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 3 findings: 0 critical, 2 high, 0 medium, and 1 low severity. Key findings include Node lockfile missing, Potential Command Injection via Unsanitized User Input to Shell Commands.
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 13, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings3
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Potential Command Injection via Unsanitized User Input to Shell Commands The skill instructs the agent to execute external Node.js scripts (`normalize-tools.js`, `submit.js`) using shell commands. Arguments passed to these scripts, such as `--title`, `--hook`, `--problem`, `--solution`, `--skills`, `--requirements`, and the input for `normalize-tools.js`, are derived from user conversation history and user-approved content. If the agent constructs these shell commands by directly concatenating user-controlled strings without proper shell escaping or quoting, a malicious user could inject arbitrary shell commands. Although the examples in `SKILL.md` show quoted arguments, the explicit instruction to the agent does not guarantee this sanitization will be applied to dynamic, user-derived content. The agent implementation must ensure all user-derived arguments passed to `node` commands are properly shell-escaped or quoted. For example, using a library function that safely escapes strings for shell execution, or ensuring that the agent explicitly wraps all such arguments in single quotes (e.g., `node submit.js --title '$USER_TITLE'`). This applies to all arguments derived from user input for `normalize-tools.js` and `submit.js`. | LLM | SKILL.md:69 | |
| HIGH | Potential Command Injection via Unsanitized User Input to Shell Commands The skill instructs the agent to execute external Node.js scripts (`normalize-tools.js`, `submit.js`) using shell commands. Arguments passed to these scripts, such as `--title`, `--hook`, `--problem`, `--solution`, `--skills`, `--requirements`, and the input for `normalize-tools.js`, are derived from user conversation history and user-approved content. If the agent constructs these shell commands by directly concatenating user-controlled strings without proper shell escaping or quoting, a malicious user could inject arbitrary shell commands. Although the examples in `SKILL.md` show quoted arguments, the explicit instruction to the agent does not guarantee this sanitization will be applied to dynamic, user-derived content. The agent implementation must ensure all user-derived arguments passed to `node` commands are properly shell-escaped or quoted. For example, using a library function that safely escapes strings for shell execution, or ensuring that the agent explicitly wraps all such arguments in single quotes (e.g., `node submit.js --title '$USER_TITLE'`). This applies to all arguments derived from user input for `normalize-tools.js` and `submit.js`. | LLM | SKILL.md:169 | |
| LOW | Node lockfile missing package.json is present but no lockfile was found (package-lock.json, pnpm-lock.yaml, or yarn.lock). Commit a lockfile for deterministic dependency resolution. | Dependencies | skills/josephl37/share-usecase/package.json |
Scan History
Embed Code
[](https://skillshield.io/report/a078de5db3ef6b91)
Powered by SkillShield