Security Audit
architecture-decision-records
github.com/sickn33/antigravity-awesome-skillsTrust Assessment
architecture-decision-records received a trust score of 60/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Potential Command Injection via Shell Code Blocks.
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 20, 2026 (commit e36d6fd3). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Potential Command Injection via Shell Code Blocks The skill documentation contains shell command examples within a markdown code block. If the host LLM is susceptible to prompt injection and is instructed to execute code blocks found in untrusted content, these commands could be executed. Specifically, `brew install adr-tools` could lead to arbitrary software installation on the host system, and `adr generate toc > docs/adr/README.md` could lead to arbitrary file writes, potentially overwriting critical files or introducing malicious content. 1. Ensure the host LLM environment is strictly sandboxed and cannot execute arbitrary shell commands found in skill content. 2. If the skill is intended for LLM execution, explicitly define which commands are safe to execute and sanitize any user-provided inputs to those commands. 3. For documentation-only skills, ensure the LLM is strictly instructed not to execute any code blocks. 4. Consider using a different format for presenting commands if they are purely illustrative and not meant for LLM execution, or add explicit warnings against execution. | LLM | SKILL.md:200 |
Scan History
Embed Code
[](https://skillshield.io/report/f3c479db420bf0b3)
Powered by SkillShield