Trust Assessment
bank-skill received a trust score of 90/100, placing it in the Trusted category. This skill has passed all critical security checks and demonstrates strong security practices.
SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Potential Command Injection via untrusted skill inputs.
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 14, 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 | |
|---|---|---|---|---|
| HIGH | Potential Command Injection via untrusted skill inputs The skill's `Manifest` indicates it uses the `python` binary, and the `SKILL.md` describes that the skill accepts various arbitrary string inputs (e.g., `recipientName`, `recipientAccount`, `recipientAddress`) via JSON piped to `./run.sh`. If the `run.sh` script or the underlying Python code constructs shell commands or uses functions like `eval()` or `subprocess.run(shell=True)` with these untrusted inputs without proper sanitization (e.g., `shlex.quote`), it could lead to command injection. An attacker could craft malicious input to execute arbitrary commands on the host system, potentially leading to data exfiltration or system compromise. Ensure all user-provided inputs are strictly validated and sanitized before being used in any shell command execution. For Python, use `subprocess.run` with `shell=False` and pass arguments as a list, or use `shlex.quote` for individual arguments if `shell=True` is unavoidable. Ideally, avoid constructing shell commands with user input altogether. Provide the `run.sh` script and any Python code for a full security review to confirm proper input handling. | LLM | SKILL.md:79 |
Scan History
Embed Code
[](https://skillshield.io/report/df1cdeef0e29dd37)
Powered by SkillShield