Trust Assessment
aws-advisor received a trust score of 85/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Shell Command Injection via Untrusted User Input in Workflows.
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 1, 2026 (commit 120b6767). 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 | Shell Command Injection via Untrusted User Input in Workflows The skill workflows and script usage instructions suggest piping user-supplied input directly into shell commands (e.g., using `echo "<user_input>" | python script.py`). If the user's input contains shell metacharacters (such as `;`, `&&`, `|`, or `$()`), it can lead to arbitrary command execution on the host machine running the AI agent. Avoid instructing the LLM to use shell pipelines with untrusted user input. Instead, have the LLM write the user's input to a temporary file first and then run the script by redirecting the file (e.g., `python scripts/well_architected_review.py < temp_input.txt`), or pass the file path as an argument to the script. | LLM | SKILL.md:105 |
Scan History
Embed Code
[](https://skillshield.io/report/56bee8d7c4143517)
Powered by SkillShield