Trust Assessment
cow-swap received a trust score of 65/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 2 findings: 1 critical, 0 high, 1 medium, and 0 low severity. Key findings include Sensitive environment variable access: $USER, Potential Command Injection via Unsanitized User Input in Shell Commands.
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 | |
|---|---|---|---|---|
| CRITICAL | Potential Command Injection via Unsanitized User Input in Shell Commands The skill constructs shell commands using `curl` and directly interpolates user-controlled variables (e.g., `FROM_ADDRESS`, `SELL_TOKEN`, `BUY_TOKEN`, `SELL_AMOUNT`, `QUOTE_ID`, `ORDER_UID`, `USER_ADDRESS`, `EIP712_SIGNATURE`, `CANCELLATION_SIGNATURE`) into the command string without proper sanitization or escaping. A malicious user could craft these input variables to inject arbitrary shell commands, leading to remote code execution in the skill's environment. This vulnerability is present in the construction of JSON payloads within the `curl -d` arguments, where an attacker could break out of the JSON string and execute arbitrary commands. All user-controlled inputs must be rigorously sanitized and shell-escaped before being interpolated into shell commands. For JSON payloads, ensure that inputs are properly JSON-escaped to prevent both JSON structure manipulation and shell command injection. Consider using a robust library or framework for constructing API requests that handles input sanitization automatically, rather than direct string concatenation in shell scripts. | LLM | SKILL.md:40 | |
| MEDIUM | Sensitive environment variable access: $USER Access to sensitive environment variable '$USER' detected in shell context. Verify this environment variable access is necessary and the value is not exfiltrated. | Static | skills/0xterrybit/cow-swap/SKILL.md:116 |
Scan History
Embed Code
[](https://skillshield.io/report/3ce27c305d2d0e84)
Powered by SkillShield