Trust Assessment
og-image-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 9 findings: 3 critical, 2 high, 0 medium, and 4 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 Findings9
| 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/og-image-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/og-image-design/SKILL.md:9 | |
| CRITICAL | Arbitrary code execution via unverified remote script The skill includes a command `curl -fsSL https://cli.inference.sh | sh` which downloads and executes an arbitrary shell script from an external URL. This poses a critical supply chain risk and command injection vulnerability, as a compromised or malicious remote script could execute any command on the host system. This also implies broader Bash execution capabilities than the declared `Bash(infsh *)` permission. Avoid direct execution of remote scripts. If the `inference.sh` CLI is required, provide instructions for manual, verified installation or use a package manager with integrity checks. Ensure all external dependencies are explicitly versioned and reviewed. If general Bash access is intended, update the `allowed-tools` declaration accordingly. | LLM | SKILL.md:10 | |
| HIGH | Declared permissions are narrower than implied usage The manifest declares `allowed-tools: Bash(infsh *)`, suggesting that only commands starting with `infsh` are permitted. However, the skill includes a general Bash command `curl -fsSL ... | sh`. If this command is executed by the agent, it indicates that the actual permissions granted are broader than declared, allowing general shell access. This constitutes excessive permissions for a skill that primarily interacts with a specific CLI tool. Align the `allowed-tools` declaration in the manifest with the actual permissions required by the skill. If general Bash access is necessary, declare `Bash(*)` explicitly. If not, remove or replace the `curl | sh` command with a method that adheres to the `Bash(infsh *)` restriction or safer installation practices. | LLM | SKILL.md:10 | |
| HIGH | Unpinned external application and skill dependencies The skill relies on external `infsh` applications (e.g., `infsh/html-to-image`, `falai/flux-dev-lora`, `tavily/search-assistant`) and `npx` skills (e.g., `inferencesh/skills@ai-image-generation`) without specifying fixed versions. This introduces a supply chain risk, as updates to these external resources could introduce vulnerabilities, breaking changes, or malicious code without explicit review or control. Pin all external application and skill dependencies to specific, immutable versions (e.g., `infsh/html-to-image@v1.2.3`, `inferencesh/skills@ai-image-generation@1.0.0`) to ensure consistency, prevent unexpected changes, and mitigate supply chain risks. | LLM | SKILL.md:16 | |
| 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/og-image-design/SKILL.md:13 | |
| 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/og-image-design/SKILL.md:98 | |
| 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/og-image-design/SKILL.md:106 | |
| 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/og-image-design/SKILL.md:114 |
Scan History
Embed Code
[](https://skillshield.io/report/764fbf750825cf7f)
Powered by SkillShield