Trust Assessment
skillscanner received a trust score of 73/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 1 finding: 1 critical, 0 high, 0 medium, and 0 low severity. Key findings include Potential Command Injection via unsanitized user input 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 | |
|---|---|---|---|---|
| CRITICAL | Potential Command Injection via unsanitized user input in curl command The skill instructs the agent to construct and execute a `curl` command where user-provided values (`AUTHOR` and `SKILL_SLUG`) are directly substituted into the `--data` payload. The `skillUrl` is embedded within a single-quoted JSON string for the `--data` argument. If these user-provided values contain shell metacharacters (e.g., single quotes, backticks, semicolons), an attacker could inject arbitrary shell commands, leading to remote code execution on the agent's host. This is a common vulnerability when agents construct shell commands with unsanitized user input. Instruct the agent to properly sanitize and escape all user-provided inputs (`AUTHOR`, `SKILL_SLUG`) before constructing the `curl` command. Specifically, ensure that the `skillUrl` value is correctly JSON-escaped and then shell-escaped if the command is executed via a shell (e.g., `subprocess.run(shell=True)`). Prefer using a list-based execution (e.g., `subprocess.run(['curl', ..., '--data', json_payload])`) with a properly formed JSON string to avoid shell injection entirely. | LLM | SKILL.md:12 |
Scan History
Embed Code
[](https://skillshield.io/report/84fd1a653fdc798d)
Powered by SkillShield