Security Audit
giil
github.com/Mrc220/agent_flywheel_clawdbot_skills_and_integrationsTrust Assessment
giil 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 9 findings: 8 critical, 1 high, 0 medium, and 0 low severity. Key findings include Arbitrary command execution, Remote code execution: curl/wget pipe to shell, Insecure `curl | bash` installation method.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Manifest Analysis layer scored lowest at 0/100, indicating areas for improvement.
Last analyzed on June 1, 2026 (commit 6a655802). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings9
| 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/giil/SKILL.md:47 | |
| 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/giil/SKILL.md:419 | |
| 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/giil/SKILL.md:422 | |
| 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/giil/SKILL.md:425 | |
| 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/giil/SKILL.md:47 | |
| 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/giil/SKILL.md:419 | |
| 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/giil/SKILL.md:422 | |
| 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/giil/SKILL.md:425 | |
| HIGH | Insecure `curl | bash` installation method The recommended installation method for 'giil' involves piping a script directly from `raw.githubusercontent.com` to `bash`. This practice, often referred to as 'curl | bash', executes arbitrary code from an external source without prior review or verification by default. A compromise of the GitHub repository (Dicklesworthstone/giil) or the `raw.githubusercontent.com` CDN could lead to arbitrary code execution on the user's system with the permissions of the user running the command. While a `GIIL_VERIFY=1` option is mentioned for a 'Verified installation', it is not the default, leaving users vulnerable to supply chain attacks. Recommend users download the `install.sh` script, review its contents, and then execute it locally (`bash install.sh`). Alternatively, provide a package manager installation (e.g., Homebrew, apt, yum) that includes checksum verification, or distribute signed binaries. If `GIIL_VERIFY=1` provides robust checksum verification, make it the default behavior or clearly instruct users to always use it as the primary installation method. | Static | SKILL.md:39 |
Scan History
Embed Code
[](https://skillshield.io/report/33a9b5f42f834a71)
Powered by SkillShield