Trust Assessment
dupe received a trust score of 86/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Command Injection via User-Provided URL in `curl` command.
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 Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Command Injection via User-Provided URL in `curl` command The skill instructs the LLM to construct and execute `curl` commands by directly embedding user-provided `productUrl` or `imageUrl` values into the JSON payload within the `--data` argument. If the LLM or its execution environment does not properly sanitize or escape these user inputs before shell execution, a malicious user could inject arbitrary shell commands. For example, providing a URL like `https://example.com", "limit": 7 }' ; evil_command ; #` could lead to `evil_command` being executed on the host system, as it breaks out of the JSON string and the shell's single-quoted argument. The LLM's execution environment must strictly sanitize and escape all user-provided inputs before interpolating them into shell commands. Specifically, ensure that any user-provided URL is properly JSON-escaped and shell-escaped when constructing the `curl` command. Alternatively, use a safer method for making HTTP requests that does not involve direct shell command execution with user input, or implement robust input validation to ensure the URL conforms to expected patterns and does not contain shell metacharacters. | LLM | SKILL.md:15 |
Scan History
Embed Code
[](https://skillshield.io/report/2d53179eef6dc872)
Powered by SkillShield