Trust Assessment
data-exfiltrator 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 8 findings: 4 critical, 2 high, 2 medium, and 0 low severity. Key findings include Network egress to untrusted endpoints, Arbitrary command execution, Dangerous call: eval().
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Manifest Analysis layer scored lowest at 40/100, indicating areas for improvement.
Last analyzed on July 1, 2026 (commit 41fec4a9). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings8
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Network egress to untrusted endpoints Python requests POST/PUT to URL Review all outbound network calls. Remove connections to webhook collectors, paste sites, and raw IP addresses. Legitimate API calls should use well-known service domains. | Manifest | evals/test_skills/malicious/exfiltrator/analyze.py:35 | |
| 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 | evals/test_skills/malicious/exfiltrator/analyze.py:38 | |
| CRITICAL | Dangerous call: eval() Call to 'eval()' detected in function 'analyze'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | evals/test_skills/malicious/exfiltrator/analyze.py:38 | |
| CRITICAL | Data Exfiltration to External Server The analyze function reads the contents of a user-specified file and sends it to an external, untrusted server (https://evil.example.com/collect) via an HTTP POST request, leading to unauthorized data exposure. Remove the HTTP POST request to the external server. Ensure any data transmission is explicitly authorized by the user and sent to trusted endpoints. | LLM | analyze.py:35 | |
| HIGH | Potential data exfiltration: file read + network send Function 'analyze' reads files and sends data over the network. This may indicate data exfiltration. Review this function to ensure file contents are not being sent to external servers. | Static | evals/test_skills/malicious/exfiltrator/analyze.py:28 | |
| HIGH | Credential Harvesting of API Key The analyze function retrieves the API_KEY environment variable and transmits it to an external server, exposing sensitive credentials. Do not access or transmit sensitive environment variables like API keys to external endpoints. | LLM | analyze.py:32 | |
| 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 | evals/test_skills/malicious/exfiltrator/analyze.py:21 | |
| MEDIUM | Use of Unsafe eval Function The code uses the built-in eval function. Although currently hardcoded, using eval is a dangerous practice that can easily lead to arbitrary code execution if untrusted input is introduced. Avoid using eval(). Use safer alternatives like ast.literal_eval or standard arithmetic operations. | LLM | analyze.py:38 |
Scan History
Embed Code
[](https://skillshield.io/report/6cd2f1ef2d6a3e0d)
Powered by SkillShield