Trust Assessment
clawbridge 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 6 findings: 2 critical, 2 high, 1 medium, and 1 low severity. Key findings include Arbitrary command execution, Remote code execution: curl/wget pipe to shell, Node lockfile missing.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The LLM Behavioral Safety layer scored lowest at 63/100, 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 Findings6
| 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/lich2000117/clawbridge-skill-latest/SKILL.md:59 | |
| 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/lich2000117/clawbridge-skill-latest/SKILL.md:59 | |
| HIGH | Unsafe `curl | bash` installation method The skill's installation instructions, specified in the manifest, use `curl -fsSL ... | bash`. This method executes a remote script directly without integrity checks or version pinning. This is a significant supply chain risk, as a compromise of the remote server (`clawbridge.cloud`) or a man-in-the-middle attack could lead to arbitrary code execution on the host system during installation. Recommend using a package manager, verifying checksums, or pinning to a specific version of the install script. Avoid direct `curl | bash` for production systems. | LLM | SKILL.md | |
| HIGH | Potential command injection via user-supplied arguments The skill description indicates it executes `clawbridge run` and allows arguments such as `--profile` (e.g., `/clawbridge --profile myprofile`). If the value for `--profile` (or any other argument) is constructed directly from unsanitized user input, a malicious user could inject arbitrary shell commands (e.g., `/clawbridge --profile "myprofile; rm -rf /"`), leading to command injection on the host system. Ensure all user-supplied arguments passed to external commands are strictly validated and sanitized. Prefer passing arguments as a list to the execution environment rather than concatenating them into a single shell string. | LLM | SKILL.md:27 | |
| MEDIUM | Reliance on external, unverified binary with potential for broad permissions The skill's core functionality is to execute an external `clawbridge` binary. The security, behavior, and permissions of this binary are critical and outside the direct control of the skill itself. If the `clawbridge` binary is compromised, contains vulnerabilities, or is designed with excessive permissions, the skill could inadvertently facilitate malicious actions on the host system by simply invoking it. Users should be made aware of the trust implications of installing and running external binaries. The skill developer should provide assurances about the security and scope of the `clawbridge` binary, and ideally, the skill should operate with the principle of least privilege. | LLM | SKILL.md:17 | |
| LOW | Node lockfile missing package.json is present but no lockfile was found (package-lock.json, pnpm-lock.yaml, or yarn.lock). Commit a lockfile for deterministic dependency resolution. | Dependencies | skills/lich2000117/clawbridge-skill-latest/package.json |
Scan History
Embed Code
[](https://skillshield.io/report/4c78cdfdc0cdd8f3)
Powered by SkillShield