Trust Assessment
landing-page-design received a trust score of 10/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 5 findings: 4 critical, 0 high, 0 medium, and 1 low severity. Key findings include Covert behavior / concealment directives, Arbitrary command execution, Remote code execution: curl/wget pipe to shell.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The LLM Behavioral Safety layer scored lowest at 40/100, 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 Findings5
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Arbitrary command execution Remote code download piped to interpreter Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands. | Manifest | skills/okaris/landing-page-design/SKILL.md:9 | |
| CRITICAL | Remote code execution: curl/wget pipe to shell Detected a pattern that downloads and immediately executes remote code. This is a primary malware delivery vector. Never pipe curl/wget output directly to a shell interpreter. | Static | skills/okaris/landing-page-design/SKILL.md:9 | |
| CRITICAL | Unauthorized execution of `curl | sh` command The skill attempts to execute `curl` and pipe its output directly to `sh`. The declared permissions for this skill are `Bash(infsh *)`, meaning only commands starting with `infsh` are explicitly allowed. Executing `curl` and `sh` constitutes a command injection attempt, as it bypasses the intended tool restrictions. Furthermore, this command downloads and executes an unpinned remote script, introducing a significant supply chain risk where a compromise of the remote server (`cli.inference.sh`) could lead to arbitrary code execution on the host system. Restrict the skill's execution environment to only allow explicitly permitted commands (`infsh` in this case). Ensure that `curl` and `sh` are not accessible or executable by the skill. If remote script execution is truly required, it must be explicitly allowed and include robust integrity checks (e.g., hash verification) and version pinning. | LLM | SKILL.md:8 | |
| CRITICAL | Unauthorized execution of `npx` command The skill attempts to execute `npx`, which is a Node.js package runner. The declared permissions for this skill are `Bash(infsh *)`, meaning only commands starting with `infsh` are explicitly allowed. Executing `npx` constitutes a command injection attempt, as it bypasses the intended tool restrictions and could lead to arbitrary code execution if `npx` is available on the system. This also introduces a supply chain risk as `npx` can download and execute unverified packages. Restrict the skill's execution environment to only allow explicitly permitted commands (`infsh` in this case). Ensure that `npx` or other unauthorized executables are not accessible or executable by the skill. If `npx` functionality is truly required, it must be explicitly added to the `allowed-tools` manifest. | LLM | SKILL.md:203 | |
| LOW | Covert behavior / concealment directives CSS-based text hiding Remove hidden instructions, zero-width characters, and bidirectional overrides. Skill instructions should be fully visible and transparent to users. | Manifest | skills/okaris/landing-page-design/SKILL.md:201 |
Scan History
Embed Code
[](https://skillshield.io/report/2e8076b327d5486f)
Powered by SkillShield