Trust Assessment
quantum-lab received a trust score of 58/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 3 findings: 1 critical, 0 high, 2 medium, and 0 low severity. Key findings include Sensitive environment variable access: $HOME, Arbitrary command execution via 'exec "$@"'.
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 Findings3
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Arbitrary command execution via 'exec "$@"' The `scripts/qexec.sh` script directly executes all arguments passed to it using `exec "$@"` on line 28. This design allows for arbitrary command injection. An attacker could craft malicious input (e.g., by including shell metacharacters like `;` or `&&`, or by specifying a different executable like `bash` or `sh`) that the LLM might then pass to `qexec.sh`. For instance, if the LLM is prompted to execute `qexec.sh bash -c 'rm -rf /'`, the script would directly execute this command, leading to severe compromise of the agent's environment. Modify `scripts/qexec.sh` to explicitly call only the intended interpreter (e.g., `python`) and pass only the necessary, sanitized arguments to it. Implement strict argument parsing and whitelisting within `qexec.sh` or its wrapper scripts (`gl`, `ql`) to ensure only approved commands and arguments are executed. For example, if the skill is only meant to run specific Python scripts, the `qexec.sh` script should validate the Python script name and its arguments against a whitelist before execution. | LLM | scripts/qexec.sh:28 | |
| MEDIUM | Sensitive environment variable access: $HOME Access to sensitive environment variable '$HOME' detected in shell context. Verify this environment variable access is necessary and the value is not exfiltrated. | Static | skills/bramdo/quantumlab/SKILL.md:35 | |
| MEDIUM | Sensitive environment variable access: $HOME Access to sensitive environment variable '$HOME' detected in shell context. Verify this environment variable access is necessary and the value is not exfiltrated. | Static | skills/bramdo/quantumlab/scripts/qexec.sh:4 |
Scan History
Embed Code
[](https://skillshield.io/report/dcd6df37a5e36c34)
Powered by SkillShield