Trust Assessment
cryptocurrency-trader 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 32 findings: 5 critical, 7 high, 19 medium, and 1 low severity. Key findings include Unsafe environment variable passthrough, File read + network send exfiltration, Credential harvesting.
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 Findings32
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | File read + network send exfiltration AI agent config/credential file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality. | Manifest | skills/veeramanikandanr48/cryptocurrency-trader-skill/test_claude_code_compat.sh:64 | |
| CRITICAL | File read + network send exfiltration AI agent config/credential file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality. | Manifest | skills/veeramanikandanr48/cryptocurrency-trader-skill/test_claude_code_compat.sh:67 | |
| CRITICAL | File read + network send exfiltration AI agent config/credential file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality. | Manifest | skills/veeramanikandanr48/cryptocurrency-trader-skill/test_claude_code_compat.sh:71 | |
| CRITICAL | Credential harvesting Reading well-known credential environment variables Skills should only access environment variables they explicitly need. Bulk environment dumps (os.environ.copy, JSON.stringify(process.env)) are almost always malicious. Remove access to Keychain, GPG keys, and credential stores. | Manifest | skills/veeramanikandanr48/cryptocurrency-trader-skill/llm_trading_assistant.py:119 | |
| CRITICAL | Credential harvesting Reading well-known credential environment variables Skills should only access environment variables they explicitly need. Bulk environment dumps (os.environ.copy, JSON.stringify(process.env)) are almost always malicious. Remove access to Keychain, GPG keys, and credential stores. | Manifest | skills/veeramanikandanr48/cryptocurrency-trader-skill/llm_trading_assistant.py:137 | |
| HIGH | Unsafe environment variable passthrough Access to well-known credential environment variables Minimize environment variable exposure. Only pass required, non-sensitive variables to MCP servers. Use dedicated secret management instead of environment passthrough. | Manifest | skills/veeramanikandanr48/cryptocurrency-trader-skill/llm_trading_assistant.py:119 | |
| HIGH | Unsafe environment variable passthrough Access to well-known credential environment variables Minimize environment variable exposure. Only pass required, non-sensitive variables to MCP servers. Use dedicated secret management instead of environment passthrough. | Manifest | skills/veeramanikandanr48/cryptocurrency-trader-skill/llm_trading_assistant.py:137 | |
| HIGH | Unsafe deserialization / dynamic eval Decryption followed by code execution Remove obfuscated code execution patterns. Legitimate code does not need base64-encoded payloads executed via eval, encrypted-then-executed blobs, or dynamic attribute resolution to call system functions. | Manifest | skills/veeramanikandanr48/cryptocurrency-trader-skill/scripts/backtester.py:5 | |
| HIGH | Unsafe deserialization / dynamic eval Decryption followed by code execution Remove obfuscated code execution patterns. Legitimate code does not need base64-encoded payloads executed via eval, encrypted-then-executed blobs, or dynamic attribute resolution to call system functions. | Manifest | skills/veeramanikandanr48/cryptocurrency-trader-skill/scripts/backtester.py:477 | |
| HIGH | Sensitive path access: AI agent config Access to AI agent config path detected: '~/.claude/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | skills/veeramanikandanr48/cryptocurrency-trader-skill/test_claude_code_compat.sh:64 | |
| HIGH | Sensitive path access: AI agent config Access to AI agent config path detected: '~/.claude/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | skills/veeramanikandanr48/cryptocurrency-trader-skill/test_claude_code_compat.sh:67 | |
| HIGH | Sensitive path access: AI agent config Access to AI agent config path detected: '~/.claude/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | skills/veeramanikandanr48/cryptocurrency-trader-skill/test_claude_code_compat.sh:71 | |
| MEDIUM | Unsafe deserialization / dynamic eval Decryption followed by code execution Remove obfuscated code execution patterns. Legitimate code does not need base64-encoded payloads executed via eval, encrypted-then-executed blobs, or dynamic attribute resolution to call system functions. | Manifest | skills/veeramanikandanr48/cryptocurrency-trader-skill/scripts/backtest_validator.py:68 | |
| MEDIUM | Unsafe deserialization / dynamic eval Decryption followed by code execution Remove obfuscated code execution patterns. Legitimate code does not need base64-encoded payloads executed via eval, encrypted-then-executed blobs, or dynamic attribute resolution to call system functions. | Manifest | skills/veeramanikandanr48/cryptocurrency-trader-skill/scripts/backtest_validator.py:77 | |
| MEDIUM | Unsafe deserialization / dynamic eval Decryption followed by code execution Remove obfuscated code execution patterns. Legitimate code does not need base64-encoded payloads executed via eval, encrypted-then-executed blobs, or dynamic attribute resolution to call system functions. | Manifest | skills/veeramanikandanr48/cryptocurrency-trader-skill/scripts/backtest_validator.py:82 | |
| MEDIUM | Unsafe deserialization / dynamic eval Decryption followed by code execution Remove obfuscated code execution patterns. Legitimate code does not need base64-encoded payloads executed via eval, encrypted-then-executed blobs, or dynamic attribute resolution to call system functions. | Manifest | skills/veeramanikandanr48/cryptocurrency-trader-skill/scripts/backtest_validator.py:87 | |
| MEDIUM | Unsafe deserialization / dynamic eval Decryption followed by code execution Remove obfuscated code execution patterns. Legitimate code does not need base64-encoded payloads executed via eval, encrypted-then-executed blobs, or dynamic attribute resolution to call system functions. | Manifest | skills/veeramanikandanr48/cryptocurrency-trader-skill/scripts/backtest_validator.py:388 | |
| MEDIUM | Unsafe deserialization / dynamic eval Decryption followed by code execution Remove obfuscated code execution patterns. Legitimate code does not need base64-encoded payloads executed via eval, encrypted-then-executed blobs, or dynamic attribute resolution to call system functions. | Manifest | skills/veeramanikandanr48/cryptocurrency-trader-skill/scripts/backtest_validator.py:399 | |
| MEDIUM | Unsafe deserialization / dynamic eval Decryption followed by code execution Remove obfuscated code execution patterns. Legitimate code does not need base64-encoded payloads executed via eval, encrypted-then-executed blobs, or dynamic attribute resolution to call system functions. | Manifest | skills/veeramanikandanr48/cryptocurrency-trader-skill/scripts/backtester.py:572 | |
| MEDIUM | Unsafe deserialization / dynamic eval Decryption followed by code execution Remove obfuscated code execution patterns. Legitimate code does not need base64-encoded payloads executed via eval, encrypted-then-executed blobs, or dynamic attribute resolution to call system functions. | Manifest | skills/veeramanikandanr48/cryptocurrency-trader-skill/scripts/config.py:6 | |
| MEDIUM | Unsafe deserialization / dynamic eval Decryption followed by code execution Remove obfuscated code execution patterns. Legitimate code does not need base64-encoded payloads executed via eval, encrypted-then-executed blobs, or dynamic attribute resolution to call system functions. | Manifest | skills/veeramanikandanr48/cryptocurrency-trader-skill/scripts/system_health_monitor.py:5 | |
| MEDIUM | Unsafe deserialization / dynamic eval Decryption followed by code execution Remove obfuscated code execution patterns. Legitimate code does not need base64-encoded payloads executed via eval, encrypted-then-executed blobs, or dynamic attribute resolution to call system functions. | Manifest | skills/veeramanikandanr48/cryptocurrency-trader-skill/scripts/trading_agent.py:4 | |
| MEDIUM | Unsafe deserialization / dynamic eval Decryption followed by code execution Remove obfuscated code execution patterns. Legitimate code does not need base64-encoded payloads executed via eval, encrypted-then-executed blobs, or dynamic attribute resolution to call system functions. | Manifest | skills/veeramanikandanr48/cryptocurrency-trader-skill/tests/test_core_modules.py:308 | |
| MEDIUM | Unpinned Python dependency version Requirement 'ccxt>=4.0.0' is not pinned to an exact version. Pin Python dependencies with '==<exact version>'. | Dependencies | skills/veeramanikandanr48/cryptocurrency-trader-skill/requirements.txt:1 | |
| MEDIUM | Unpinned Python dependency version Requirement 'pandas>=2.0.0' is not pinned to an exact version. Pin Python dependencies with '==<exact version>'. | Dependencies | skills/veeramanikandanr48/cryptocurrency-trader-skill/requirements.txt:2 | |
| MEDIUM | Unpinned Python dependency version Requirement 'numpy>=1.24.0' is not pinned to an exact version. Pin Python dependencies with '==<exact version>'. | Dependencies | skills/veeramanikandanr48/cryptocurrency-trader-skill/requirements.txt:3 | |
| MEDIUM | Unpinned Python dependency version Requirement 'scipy>=1.11.0' is not pinned to an exact version. Pin Python dependencies with '==<exact version>'. | Dependencies | skills/veeramanikandanr48/cryptocurrency-trader-skill/requirements.txt:4 | |
| MEDIUM | Unpinned Python dependency version Requirement 'scikit-learn>=1.3.0' is not pinned to an exact version. Pin Python dependencies with '==<exact version>'. | Dependencies | skills/veeramanikandanr48/cryptocurrency-trader-skill/requirements.txt:5 | |
| MEDIUM | Unpinned Python dependency version Requirement 'statsmodels>=0.14.0' is not pinned to an exact version. Pin Python dependencies with '==<exact version>'. | Dependencies | skills/veeramanikandanr48/cryptocurrency-trader-skill/requirements.txt:6 | |
| MEDIUM | Unpinned Python dependency version Requirement 'ta>=0.11.0' is not pinned to an exact version. Pin Python dependencies with '==<exact version>'. | Dependencies | skills/veeramanikandanr48/cryptocurrency-trader-skill/requirements.txt:7 | |
| MEDIUM | Unpinned Python dependency version Requirement 'pyyaml>=6.0.0' is not pinned to an exact version. Pin Python dependencies with '==<exact version>'. | Dependencies | skills/veeramanikandanr48/cryptocurrency-trader-skill/requirements.txt:8 | |
| LOW | Unpinned or Broadly Pinned Dependencies The 'requirements.txt' file specifies dependencies using broad version ranges (e.g., 'package>=X.Y.Z') instead of exact versions ('package==X.Y.Z'). This practice can introduce supply chain risks, as newer, potentially vulnerable or incompatible versions of packages could be installed without explicit review. While this allows for automatic updates to minor and patch versions, it also means that a malicious or buggy update within the specified major version range could affect the skill's security or stability. Pin all dependencies to exact versions (e.g., 'package==X.Y.Z') in 'requirements.txt'. Regularly review and manually update these pinned versions to incorporate necessary security patches and bug fixes, ensuring compatibility and security. | LLM | requirements.txt:1 |
Scan History
Embed Code
[](https://skillshield.io/report/50e60a5171ba1244)
Powered by SkillShield