Trust Assessment
ai-image-generation 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 4 findings: 3 critical, 1 high, 0 medium, and 0 low severity. Key findings include Arbitrary command execution, Remote code execution: curl/wget pipe to shell, Command execution exceeding declared permissions.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The LLM Behavioral Safety layer scored lowest at 55/100, 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 Findings4
| 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/ai-image-generation/SKILL.md:10 | |
| 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/ai-image-generation/SKILL.md:10 | |
| CRITICAL | Command execution exceeding declared permissions The skill demonstrates a `curl | sh` command which attempts to download and execute a shell script from a remote URL. This action critically exceeds the skill's declared permission `Bash(infsh *)`, which only allows commands starting with `infsh`. If the runtime environment does not strictly enforce these declared permissions, this command poses a severe command injection and supply chain risk, allowing arbitrary code execution from an external source without proper validation or sandboxing. Remove commands that exceed the skill's declared permissions. If this functionality is absolutely required, the skill's `allowed-tools` declaration must be updated to `Bash(*)` or `Bash(curl *)` and `Bash(sh *)`, which would significantly increase the skill's attack surface and require strong justification. Prefer using a package manager with signed packages and version pinning instead of direct remote script execution. | LLM | SKILL.md:9 | |
| HIGH | Package execution exceeding declared permissions The skill demonstrates `npx skills add` commands which attempt to execute an `npm` package. This action exceeds the skill's declared permission `Bash(infsh *)`, which only allows commands starting with `infsh`. If the runtime environment does not strictly enforce these declared permissions, these commands introduce a command injection and supply chain risk, as `npx` fetches and executes packages from the npm registry. The packages are not version-pinned in these examples, increasing the risk of unexpected or malicious updates. Remove commands that exceed the skill's declared permissions. If this functionality is absolutely required, the skill's `allowed-tools` declaration must be updated to `Bash(*)` or `Bash(npx *)`, which would significantly increase the skill's attack surface and require strong justification. If `npx` must be used, ensure package names and arguments are strictly controlled and version-pinned (e.g., `package@1.2.3`). | LLM | SKILL.md:90 |
Scan History
Embed Code
[](https://skillshield.io/report/7d918f4d8f357afa)
Powered by SkillShield