Trust Assessment
skill-guard 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 5 findings: 3 critical, 1 high, 1 medium, and 0 low severity. Key findings include Arbitrary command execution, Remote code execution: curl/wget pipe to shell, Sensitive environment variable access: $HOME.
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 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/jamesouttake/skill-guard/scripts/safe-install.sh:86 | |
| 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/jamesouttake/skill-guard/scripts/safe-install.sh:86 | |
| CRITICAL | Command Injection via Unquoted Variable Expansion The `VERSION_ARG` variable is constructed from user input (`$2`) and then used unquoted in the `clawhub install` command. This allows an attacker to inject arbitrary shell commands by providing a malicious string to the `--version` argument. For example, `--version '1.0; rm -rf /'` would execute `rm -rf /` after the `clawhub install` command. Always quote variables that contain user input when used in shell commands to prevent word splitting and globbing. Change `VERSION_ARG="--version $2"` to `VERSION_ARG="--version '$2'"` or ensure `$VERSION_ARG` is properly quoted when used, e.g., `clawhub install "$SKILL_SLUG" "$VERSION_ARG" --workdir "$STAGING_DIR"`. A more robust solution would be to parse arguments more carefully or use an array for command arguments. | LLM | scripts/safe-install.sh:60 | |
| HIGH | Unpinned Dependency in Security Scanner The script uses `uvx mcp-scan@latest` to execute the security scanner. Relying on `@latest` means that any new version of `mcp-scan`, including potentially malicious or buggy updates, will be automatically downloaded and executed without explicit review. This introduces a significant supply chain risk, especially for a security-critical component. Pin the `mcp-scan` dependency to a specific, known-good version (e.g., `mcp-scan@1.2.3`) or at least a major/minor version range (e.g., `mcp-scan@^1.0.0`) to ensure consistent and reviewed behavior. Regularly update the pinned version after manual verification. | LLM | scripts/safe-install.sh:110 | |
| MEDIUM | Sensitive environment variable access: $HOME Access to sensitive environment variable '$HOME' detected in shell context. Verify this environment variable access is necessary and the value is not exfiltrated. | Static | skills/jamesouttake/skill-guard/scripts/safe-install.sh:12 |
Scan History
Embed Code
[](https://skillshield.io/report/8e3dbc51d2aec610)
Powered by SkillShield