Trust Assessment
planka received a trust score of 77/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 3 findings: 0 critical, 1 high, 2 medium, and 0 low severity. Key findings include Untrusted Binary Dependency from Custom Homebrew Tap, Potential Command Injection through CLI Arguments, Credential Handling and Storage Risk.
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 12, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings3
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Untrusted Binary Dependency from Custom Homebrew Tap The skill's setup instructions require installing `planka-cli` from a custom Homebrew tap (`voydz/homebrew-tap`). Relying on a third-party, unverified tap introduces a significant supply chain risk. If the tap or the `planka-cli` package within it is compromised, malicious code could be installed and executed on the host system, leading to arbitrary code execution or data exfiltration. Avoid installing binaries from unverified custom taps. Prefer officially maintained package repositories, provide source code for review, or implement strong integrity checks (e.g., cryptographic hashes) for external dependencies. | LLM | SKILL.md:9 | |
| MEDIUM | Potential Command Injection through CLI Arguments The skill invokes the `planka-cli` tool with arguments that can be derived from user input, such as card titles (`planka-cli cards create <LIST_ID> "Card title"`). If the `planka-cli` binary (or its underlying implementation) does not properly sanitize or escape these user-provided strings before passing them to a shell or executing them, a malicious user could inject arbitrary shell commands, leading to command injection and potential arbitrary code execution on the host system. Ensure all user-provided input passed to `planka-cli` is strictly validated and properly escaped for shell execution. The `planka-cli` tool itself must be robust against command injection vulnerabilities. | LLM | SKILL.md:49 | |
| MEDIUM | Credential Handling and Storage Risk The skill's `login` command (`planka-cli login --url ... --username ... --password ...`) explicitly handles and stores user credentials. The security of how these sensitive credentials are stored by the `planka-cli` tool is not visible in the provided context. Insecure storage mechanisms (e.g., plain text files, weak encryption, improper file permissions) could lead to the compromise of user credentials. Document the credential storage mechanism used by `planka-cli`. Ensure credentials are stored securely using industry best practices, such as strong encryption, restricted file permissions, and leveraging OS-level secret management facilities. Avoid storing sensitive credentials in plain text. | LLM | SKILL.md:17 |
Scan History
Embed Code
[](https://skillshield.io/report/0cd05b98439f7962)
Powered by SkillShield