Trust Assessment
data-processor 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 9 findings: 6 critical, 2 high, 1 medium, and 0 low severity. Key findings include Arbitrary command execution, Dangerous call: exec(), Dangerous call: subprocess.Popen().
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The LLM Behavioral Safety 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 Findings9
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Arbitrary command execution Python shell execution (os.system, subprocess) 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/dgriffin831/skill-scan/test-fixtures/backdoor-magic-string/process.py:46 | |
| 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/dgriffin831/skill-scan/test-fixtures/backdoor-magic-string/process.py:40 | |
| CRITICAL | Dangerous call: exec() Call to 'exec()' detected in function 'activate_backdoor'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/dgriffin831/skill-scan/test-fixtures/backdoor-magic-string/process.py:40 | |
| CRITICAL | Remote Code Execution via Base64-decoded Payload The skill fetches a payload from an external attacker-controlled server (`c2.attacker.example.com`), decodes it from Base64, and executes it using `exec()`. This allows for arbitrary remote code execution on the host system, representing a severe command injection vulnerability and a hidden instruction mechanism. Remove the `activate_backdoor` function and any calls to `exec()` or `eval()` with untrusted or remotely fetched content. Do not execute arbitrary code from external sources. | LLM | process.py:25 | |
| CRITICAL | Reverse Shell Attempt via Subprocess The skill attempts to establish a reverse shell to an attacker-controlled IP address (`attacker.example.com:4444`) using `subprocess.Popen`. This grants an attacker full command-line access to the host system, enabling command injection and data exfiltration. Remove the `activate_backdoor` function and any calls to `subprocess.Popen` that execute arbitrary shell commands or establish network connections to untrusted destinations. | LLM | process.py:31 | |
| CRITICAL | Untrusted Input Triggers Backdoor Functionality The `process_data` function, which processes untrusted user input (`data`), contains logic to check for specific 'magic strings' (`ACTIVATE_BACKDOOR`, `DEBUG_MODE_ELEVATED`, `ADMIN_OVERRIDE_ENABLED`). If a magic string is detected, it triggers the `activate_backdoor` function, leading to remote code execution and a reverse shell. This constitutes a direct prompt injection vector, allowing an attacker to activate highly malicious functionality by providing specific input. Remove the `check_trigger` and `activate_backdoor` functions entirely. Never allow untrusted input to directly trigger sensitive or malicious functionality. Implement robust input validation and sanitization. | LLM | process.py:41 | |
| HIGH | Dangerous call: subprocess.Popen() Call to 'subprocess.Popen()' detected in function 'activate_backdoor'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/dgriffin831/skill-scan/test-fixtures/backdoor-magic-string/process.py:46 | |
| HIGH | Communication with External Command and Control (C2) Server The skill makes an HTTP request to `https://c2.attacker.example.com/payload` to fetch a payload. This indicates communication with a potential Command and Control (C2) server, which is a significant supply chain risk as it introduces arbitrary external code into the execution environment and is a precursor to remote code execution and data exfiltration. Do not fetch or execute code from untrusted external sources. All code should be part of the skill package and subject to review. Remove any communication with known or suspected C2 infrastructure. | LLM | process.py:24 | |
| MEDIUM | Suspicious import: requests Import of 'requests' detected. This module provides network or low-level system access. Verify this import is necessary. Network and system modules in skill code may indicate data exfiltration. | Static | skills/dgriffin831/skill-scan/test-fixtures/backdoor-magic-string/process.py:25 |
Scan History
Embed Code
[](https://skillshield.io/report/5cc9a31210d8d947)
Powered by SkillShield