Trust Assessment
trade-signal received a trust score of 72/100, 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: 1 critical, 0 high, 0 medium, and 0 low severity. Key findings include Arbitrary Command Execution via Python Subprocess.
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 Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Arbitrary Command Execution via Python Subprocess The `scripts/search.sh` script directly embeds user-controlled input (`$QUERY`) into a `python3 -c "..."` command. This allows an attacker to inject arbitrary Python code, which can then execute arbitrary shell commands using modules like `subprocess` or `os.system`. This is a classic command injection vulnerability. Modify the script to pass the `$QUERY` as an argument to the Python script instead of embedding it directly into the command string. For example, create a separate Python script that takes the query as a command-line argument and uses `sys.argv` to safely access it. Alternatively, use a safer shell-native URL encoding method if available, or ensure that the Python call is structured to prevent shell metacharacter interpretation (e.g., by using `xargs` or a more robust Python invocation that doesn't rely on shell interpolation of the argument). | LLM | scripts/search.sh:11 |
Scan History
Embed Code
[](https://skillshield.io/report/86beb8915d0fa4ad)
Powered by SkillShield