Trust Assessment
raindrop-api received a trust score of 86/100, 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 Unquoted environment variable in shell command.
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 11, 2026 (commit 326f2466). 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 | Unquoted environment variable in shell command The skill provides `curl` examples where the `RAINDROP_TOKEN` environment variable is used unquoted within a double-quoted string in the `Authorization` header. If the `RAINDROP_TOKEN` contains shell metacharacters (e.g., `"`, `$(...)`, or `&&`), an attacker could craft a malicious token that would allow arbitrary command injection and execution by the agent's shell. The agent should ensure proper sanitization and shell-escaping of such variables before execution. The agent should ensure that the `RAINDROP_TOKEN` variable is properly sanitized and shell-escaped before being interpolated into `curl` commands to prevent command injection. For example, if the token is expected to be a simple string, it should be enclosed in single quotes or carefully double-quoted and escaped if it contains special characters. A more robust approach for the agent would be to use a dedicated HTTP client library in a programming language that handles header construction and escaping securely, rather than relying on direct shell command interpolation. | LLM | SKILL.md:30 |
Scan History
Embed Code
[](https://skillshield.io/report/da3387a88a880fdb)
Powered by SkillShield