Security Audit
frankxai/claude-skills-library:free-skills/higgsfield-soul-id
github.com/frankxai/claude-skills-libraryTrust Assessment
frankxai/claude-skills-library:free-skills/higgsfield-soul-id received a trust score of 22/100, 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: 2 critical, 1 high, 1 medium, and 0 low severity. Key findings include Arbitrary command execution, Remote code execution: curl/wget pipe to shell, Command Injection via Unsanitized User Input.
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 October 20, 2026 (commit 93c4aad5). 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 | free-skills/higgsfield-soul-id/SKILL.md:12 | |
| 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 | free-skills/higgsfield-soul-id/SKILL.md:12 | |
| HIGH | Command Injection via Unsanitized User Input The skill instructs the LLM to execute a bash command containing user-controlled input (`<name>`) without explicit instructions to sanitize, validate, or safely escape the input. An attacker could supply a malicious name containing shell metacharacters (e.g., `;`, `&&`, `|`, backticks) to execute arbitrary commands on the host system. Instruct the LLM to strictly validate the `<name>` parameter (e.g., allowing only alphanumeric characters and rejecting any shell metacharacters) and to safely escape any user input before executing bash commands. | LLM | SKILL.md:33 | |
| MEDIUM | Unverified Remote Script Execution (curl | sh) The skill bootstrap instructions command the LLM to download and execute a shell script directly from a remote URL (`raw.githubusercontent.com`) without any integrity verification (such as a SHA-256 checksum check) or pinning to a specific commit hash. If the remote repository or DNS is compromised, this can lead to arbitrary code execution on the host system. Avoid downloading and executing arbitrary scripts directly from the internet. If necessary, pin the script to a specific commit hash, download it to a temporary file, verify its SHA-256 checksum, and then execute it, or prompt the user to install the CLI manually. | LLM | SKILL.md:11 |
Scan History
Embed Code
[](https://skillshield.io/report/e536da233cd612c2)
Powered by SkillShield