Trust Assessment
planka 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 Unpinned external binary dependency from custom Homebrew tap.
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 | Unpinned external binary dependency from custom Homebrew tap The skill's setup instructions recommend installing the `planka-cli` binary from a custom Homebrew tap (`voydz/homebrew-tap`). The installation command `brew install planka-cli` does not specify a version, meaning it will always fetch the latest available version. This lack of version pinning for an external dependency from a third-party source introduces a significant supply chain risk. A malicious update to the `planka-cli` package or a compromise of the `voydz/homebrew-tap` could lead to the execution of arbitrary code on the host system when the skill is set up or updated. 1. Consider vendoring the `planka-cli` binary or its source code if feasible, or hosting it on a trusted, controlled repository. 2. If using Homebrew, specify a pinned version for `planka-cli` (e.g., `brew install planka-cli@1.2.3`) to prevent automatic updates from introducing breaking changes or malicious code. 3. Thoroughly vet the `voydz/homebrew-tap` and the `planka-cli` project for security practices and trustworthiness. 4. Implement integrity checks (e.g., checksum verification) for downloaded binaries. | LLM | SKILL.md:10 |
Scan History
Embed Code
[](https://skillshield.io/report/bff0831fa9136724)
Powered by SkillShield