Trust Assessment
senior-data-engineer received a trust score of 10/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 12 findings: 9 critical, 0 high, 3 medium, and 0 low severity. Key findings include Persistence / self-modification instructions, Arbitrary command execution, Dangerous call: compile().
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Manifest Analysis layer scored lowest at 0/100, indicating areas for improvement.
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 Findings12
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Persistence / self-modification instructions Shell RC file modification for persistence Remove any persistence mechanisms. Skills should not modify system startup configurations, crontabs, LaunchAgents, systemd services, or shell profiles. | Manifest | skills/alirezarezvani/senior-data-engineer/scripts/data_quality_validator.py:1366 | |
| CRITICAL | Persistence / self-modification instructions Shell RC file modification for persistence Remove any persistence mechanisms. Skills should not modify system startup configurations, crontabs, LaunchAgents, systemd services, or shell profiles. | Manifest | skills/alirezarezvani/senior-data-engineer/scripts/data_quality_validator.py:1400 | |
| CRITICAL | Persistence / self-modification instructions Shell RC file modification for persistence Remove any persistence mechanisms. Skills should not modify system startup configurations, crontabs, LaunchAgents, systemd services, or shell profiles. | Manifest | skills/alirezarezvani/senior-data-engineer/scripts/data_quality_validator.py:1437 | |
| CRITICAL | Persistence / self-modification instructions Shell RC file modification for persistence Remove any persistence mechanisms. Skills should not modify system startup configurations, crontabs, LaunchAgents, systemd services, or shell profiles. | Manifest | skills/alirezarezvani/senior-data-engineer/scripts/data_quality_validator.py:1466 | |
| CRITICAL | Persistence / self-modification instructions Shell RC file modification for persistence Remove any persistence mechanisms. Skills should not modify system startup configurations, crontabs, LaunchAgents, systemd services, or shell profiles. | Manifest | skills/alirezarezvani/senior-data-engineer/scripts/data_quality_validator.py:1505 | |
| CRITICAL | Arbitrary command execution Python dynamic code execution (exec/eval/compile) Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands. | Manifest | skills/alirezarezvani/senior-data-engineer/scripts/pipeline_orchestrator.py:335 | |
| CRITICAL | Arbitrary command execution Python dynamic code execution (exec/eval/compile) Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands. | Manifest | skills/alirezarezvani/senior-data-engineer/scripts/pipeline_orchestrator.py:448 | |
| CRITICAL | Arbitrary command execution Python dynamic code execution (exec/eval/compile) Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands. | Manifest | skills/alirezarezvani/senior-data-engineer/scripts/pipeline_orchestrator.py:575 | |
| CRITICAL | Unsafe parameter interpolation in generated Airflow DAGs The `pipeline_orchestrator.py` script generates Airflow DAGs by directly interpolating user-provided `TaskConfig.params` into the generated Python code using f-strings. Specifically, string values are wrapped in single quotes (`f"{key}='{value}'"`). This allows for single-quote injection, where a malicious user can terminate the string literal and inject arbitrary Python code or shell commands (if the operator is `BashOperator` or `PythonOperator`) into the generated DAG. When this generated DAG is executed by Airflow, the injected code will run, leading to arbitrary command execution. Implement proper escaping for string parameters before interpolating them into the generated Python code. For example, use `repr(value)` or a custom escaping function that handles single quotes, backslashes, and other special characters to ensure the string is correctly represented as a literal in the generated Python code. Alternatively, use a templating engine that handles escaping automatically. | LLM | scripts/pipeline_orchestrator.py:200 | |
| MEDIUM | Dangerous call: compile() Call to 'compile()' detected in function 'validate'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/alirezarezvani/senior-data-engineer/scripts/pipeline_orchestrator.py:335 | |
| MEDIUM | Dangerous call: compile() Call to 'compile()' detected in function 'validate'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/alirezarezvani/senior-data-engineer/scripts/pipeline_orchestrator.py:448 | |
| MEDIUM | Dangerous call: compile() Call to 'compile()' detected in function 'validate'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/alirezarezvani/senior-data-engineer/scripts/pipeline_orchestrator.py:575 |
Scan History
Embed Code
[](https://skillshield.io/report/9d23895eb714e1e4)
Powered by SkillShield