Trust Assessment
flights received a trust score of 76/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 2 findings: 0 critical, 2 high, 0 medium, and 0 low severity. Key findings include Unpinned Python dependency, Potential command injection via CLI arguments.
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 13, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Unpinned Python dependency The skill instructs to install `fast-flights` without specifying a version. This makes the skill vulnerable to supply chain attacks if a malicious update is pushed to the `fast-flights` package. An attacker could introduce malware or backdoors into the dependency, which would then be installed and executed. Pin the dependency to a specific, known-good version (e.g., `pip install fast-flights==X.Y.Z`) and consider using a `requirements.txt` with hash checking for integrity. | LLM | SKILL.md:9 | |
| HIGH | Potential command injection via CLI arguments The skill describes executing a CLI tool `flights-search` with user-provided arguments (`<origin>`, `<destination>`, `<date>`, `[options]`). If the AI agent constructs this command by directly concatenating unsanitized user input into a shell command string, it creates a command injection vulnerability. Malicious input (e.g., `YYZ; rm -rf /`) could lead to arbitrary code execution. When executing external commands with user-provided arguments, ensure all arguments are properly sanitized or, preferably, passed as a list to `subprocess.run(..., shell=False)` to prevent shell interpretation of special characters. | LLM | SKILL.md:15 |
Scan History
Embed Code
[](https://skillshield.io/report/2669fa7608e3fe76)
Powered by SkillShield