Trust Assessment
iblipper received a trust score of 71/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 2 findings: 1 critical, 0 high, 0 medium, and 1 low severity. Key findings include Command Injection via unvalidated shell arguments, User data sent to external third-party service.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The LLM Behavioral Safety layer scored lowest at 68/100, indicating areas for improvement.
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 Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Command Injection via unvalidated shell arguments The `scripts/iblipper.sh` script directly interpolates user-provided arguments (`EMOTION` and `MODE`) into a double-quoted string used to construct a URL. This allows for arbitrary command execution if a malicious string containing shell metacharacters (e.g., `$(command)`, backticks, `;`, `&&`, `||`) is passed as `EMOTION` or `MODE`. The script does not validate these arguments against a whitelist of allowed values, making it vulnerable to command injection. Implement strict validation for `EMOTION` and `MODE` arguments. Only allow values from a predefined whitelist. Alternatively, ensure all user-supplied arguments are properly shell-escaped before being interpolated into any command or string that will be processed by the shell. Whitelisting is generally preferred for fixed sets of options. | LLM | scripts/iblipper.sh:69 | |
| LOW | User data sent to external third-party service The skill's core functionality involves constructing URLs that include user-provided message text and directing them to an external, third-party website (`https://andyed.github.io/iblipper2025/`). While this is the intended design for generating kinetic typography, it means that any text input by the user will be transmitted to and processed by this external service. Users should be aware of this data transfer to a third party, especially if sensitive information might be included in the message. Add a clear and prominent warning in the skill's description or usage instructions, informing users that their input message will be sent to an external third-party service for processing. Advise against including highly sensitive personal or confidential information in the messages. | LLM | SKILL.md:10 |
Scan History
Embed Code
[](https://skillshield.io/report/49d7ce68c9db025c)
Powered by SkillShield