Trust Assessment
plaid received a trust score of 82/100, 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, 1 high, 1 medium, and 0 low severity. Key findings include Skill documents command that exposes access tokens, Untrusted input used in shell commands without explicit sanitization.
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 | Skill documents command that exposes access tokens The skill explicitly warns against using the `plaid-cli tokens` command because it prints sensitive access tokens. If the AI agent is prompted to execute this command, it will expose credentials, leading to data exfiltration and potential unauthorized access to financial data. This is a direct and high-risk credential exposure vector. The AI agent must be strictly instructed never to execute `plaid-cli tokens` or any command that could expose credentials, even if requested by the user. Implement strict input validation and sanitization for any user-provided arguments that could lead to such commands. | LLM | SKILL.md:49 | |
| MEDIUM | Untrusted input used in shell commands without explicit sanitization The skill examples demonstrate `item-id-or-alias` being directly interpolated into shell commands (e.g., `plaid-cli accounts <item-id-or-alias>`). If `item-id-or-alias` is derived from untrusted user input and the `plaid-cli` tool does not sufficiently sanitize its arguments, a malicious user could potentially inject arbitrary shell commands (e.g., `my_alias; rm -rf /`). This is a common command injection pattern for CLI wrappers. The AI agent must implement robust input validation and sanitization for all user-provided arguments that are passed to `plaid-cli` commands, especially those used as identifiers or aliases. Ensure that arguments are properly quoted or escaped to prevent shell metacharacter interpretation. | LLM | SKILL.md:27 |
Scan History
Embed Code
[](https://skillshield.io/report/45b097c5c7b2428e)
Powered by SkillShield