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 Potential Command Injection via Shell Execution of Local Scripts with Untrusted Input.
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 July 1, 2026 (commit 5e8b8e75). 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 Execution of Local Scripts with Untrusted Input The skill workflows and script documentation instruct the LLM to execute local Python scripts by piping user-controlled input via the shell (e.g., using 'echo "<user_input>" | python script.py'). If the LLM executes these commands literally using a shell/bash tool, a malicious user can craft an input containing shell metacharacters (such as ';', '&&', or backticks) to execute arbitrary commands on the host system. Avoid instructing the LLM to run shell commands with inline user input. Instead, have the LLM write the user input to a temporary file first, and then run the script reading from that file, or ensure the LLM uses safe argument passing without shell interpolation. | LLM | SKILL.md:83 |
Scan History
Embed Code
[](https://skillshield.io/report/56bee8d7c4143517)
Powered by SkillShield