Trust Assessment
character-design-sheet 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, Attempted execution of unauthorized shell commands.
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/character-design-sheet/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/character-design-sheet/SKILL.md:9 | |
| CRITICAL | Attempted execution of unauthorized shell commands The skill attempts to execute `curl` and `sh` commands (`curl -fsSL https://cli.inference.sh | sh`) which are outside the explicitly declared `Bash(infsh *)` permissions. This constitutes a command injection attempt, as it tries to run arbitrary shell commands not permitted by the skill's manifest. If the host LLM were to execute this snippet, it would bypass the intended security controls. Remove or comment out the `curl ... | sh` command. If `inference.sh` CLI installation is required, it should be handled by the environment setup or explicitly allowed via broader `Bash(*)` permissions, with appropriate security review. | LLM | SKILL.md:8 | |
| HIGH | Unpinned remote script execution via curl | sh The skill instructs to download and execute a shell script directly from `https://cli.inference.sh` using `curl -fsSL ... | sh`. This method lacks version pinning or integrity checks, making it vulnerable to supply chain attacks. A compromised server or malicious script update could lead to arbitrary code execution on the host system without the user's knowledge or consent. Avoid direct execution of unpinned remote scripts. If installation is necessary, use a package manager with integrity checks, or download a specific version and verify its hash before execution. Alternatively, provide a pre-built environment or container. | LLM | SKILL.md:8 |
Scan History
Embed Code
[](https://skillshield.io/report/a7eef5a31185553a)
Powered by SkillShield