Trust Assessment
kradleverse:observe 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 Direct Shell Command Execution, Broad Local Script Execution Permissions.
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 Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Direct Shell Command Execution The skill directly executes a shell command (`~/.kradle/kradleverse/venv/bin/python ~/.kradle/kradleverse/scripts/get_observations.py --help`). While the example shown uses a static `--help` argument, the underlying mechanism allows for arbitrary shell command execution. If any part of this command string is constructed using untrusted input (e.g., arguments provided by the LLM or user), it could lead to command injection, allowing an attacker to execute arbitrary commands on the host system. Implement strict input validation and sanitization for any arguments passed to the script. Consider using a safer execution method (e.g., `subprocess.run` with `shell=False` and a list of arguments) or sandboxing the execution environment. If the script is intended to be called with dynamic arguments, ensure they are properly escaped or validated. | LLM | SKILL.md:4 | |
| HIGH | Broad Local Script Execution Permissions The skill is designed to execute a local Python script (`~/.kradle/kradleverse/scripts/get_observations.py`) directly on the host system. This grants the AI agent the ability to run arbitrary code with the permissions of the user executing the agent. This broad access can lead to data exfiltration, system modification, or further compromise if the script itself is malicious or if its execution can be manipulated. Restrict the execution environment using sandboxing technologies (e.g., Docker, gVisor, or a dedicated virtual machine). Implement a strict allowlist for executable paths and arguments. Review the `get_observations.py` script thoroughly for any unintended side effects or vulnerabilities. | LLM | SKILL.md:4 |
Scan History
Embed Code
[](https://skillshield.io/report/cc3b140bb563f2cc)
Powered by SkillShield