Trust Assessment
customer-persona received a trust score of 16/100, 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: 2 critical, 1 high, 2 medium, and 0 low severity. Key findings include Arbitrary command execution, Remote code execution: curl/wget pipe to shell, Overly broad Bash permission for infsh.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. All layers scored 70 or above, reflecting consistent security practices.
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/customer-persona/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/customer-persona/SKILL.md:9 | |
| HIGH | Untrusted remote script execution in Quick Start instructions The 'Quick Start' section instructs users to execute a remote shell script directly via 'curl -fsSL https://cli.inference.sh | sh'. This practice is a significant supply chain risk, as it bypasses code review and executes arbitrary code from an external source. If 'cli.inference.sh' were compromised, users following these instructions could have their systems compromised. Avoid direct execution of remote scripts. Recommend users to install 'infsh' via a package manager, a verified binary, or by reviewing the script content before execution. | LLM | SKILL.md:10 | |
| MEDIUM | Overly broad Bash permission for infsh The skill declares 'Bash(infsh *)' permission, allowing it to execute any command starting with 'infsh'. While the skill's examples primarily use 'infsh app run', this broad permission violates the principle of least privilege. An attacker could potentially craft a prompt to the LLM to execute other 'infsh' subcommands that might have unintended side effects (e.g., 'infsh config', 'infsh filesystem', etc.), depending on the full capabilities of the 'infsh' CLI. Restrict the 'Bash' permission to only the necessary 'infsh' subcommands, such as 'Bash(infsh app run *)', if that is the only required functionality for the skill. | LLM | SKILL.md:1 | |
| MEDIUM | Execution of external NPM packages in Related Skills instructions The 'Related Skills' section instructs users to install and execute external NPM packages via 'npx skills add inferencesh/skills@web-search'. While 'npx' is a common tool, it executes code from external sources. This introduces a supply chain risk where a compromised package or a typosquatting attack could lead to arbitrary code execution on the user's system. Advise users to verify the authenticity and integrity of external packages before installation and execution. Consider providing a more secure method for adding skills if available. | LLM | SKILL.md:200 |
Scan History
Embed Code
[](https://skillshield.io/report/3b973738a3aa84aa)
Powered by SkillShield