Trust Assessment
linkdapi received a trust score of 73/100, 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: 0 critical, 2 high, 0 medium, and 0 low severity. Key findings include Agent instructed to execute arbitrary shell commands and Python scripts, Unpinned Python dependency `linkdapi`.
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 | Agent instructed to execute arbitrary shell commands and Python scripts The skill instructs the agent to create and execute temporary Python scripts using `cat` and `uv run`. This pattern, while common for agents, introduces a high risk of command injection if the agent does not properly sanitize user-provided input before incorporating it into the generated Python script or the shell commands. An attacker could craft input that, when inserted into the script or command arguments, executes arbitrary code on the host system. Agents must rigorously sanitize all user-provided input before incorporating it into generated scripts or shell commands. Consider using safer alternatives to direct shell execution for script generation and execution, or ensure a strict allowlist for script content. | LLM | SKILL.md:110 | |
| HIGH | Unpinned Python dependency `linkdapi` The skill's Python script examples specify `dependencies = ["linkdapi"]` without a version constraint. This means that `uv` will always fetch the latest available version of the `linkdapi` package. If a malicious actor were to compromise the `linkdapi` package on PyPI and publish a backdoored version, any agent using this skill would automatically download and execute the compromised code, leading to a supply chain attack. Pin dependencies to a specific, known-good version (e.g., `"linkdapi==1.2.3"`) or at least a major/minor version range (e.g., `"linkdapi~=1.2"`). Regularly review and update pinned versions. | LLM | SKILL.md:25 |
Scan History
Embed Code
[](https://skillshield.io/report/3bf7e25f7b1d293b)
Powered by SkillShield