Trust Assessment
cosmic-database received a trust score of 46/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 6 findings: 0 critical, 2 high, 3 medium, and 1 low severity. Key findings include Suspicious import: requests, Potential data exfiltration: file read + network send, Network egress to untrusted endpoints.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Static Code Analysis layer scored lowest at 56/100, indicating areas for improvement.
Last analyzed on February 12, 2026 (commit 458b1186). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings6
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Potential data exfiltration: file read + network send Function 'download_cosmic_file' 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 | cli-tool/components/skills/scientific/cosmic-database/scripts/download_cosmic.py:103 | |
| HIGH | Insecure Credential Handling in Examples The skill's documentation and quick start examples explicitly show hardcoding sensitive credentials (email and password) directly in Python code and passing them as command-line arguments. Hardcoding credentials is a severe security anti-pattern as it exposes them in source code, version control, and potentially in logs or process lists. Passing them as command-line arguments can expose them in shell history and process lists, making them vulnerable to unauthorized access. Instruct users to use secure methods for handling credentials, such as environment variables, a dedicated secrets management service, or prompting for input at runtime. Avoid hardcoding credentials in examples or suggesting their use as direct command-line arguments. For example, use `os.getenv('COSMIC_EMAIL')` and `os.getenv('COSMIC_PASSWORD')`. | Static | SKILL.md:40 | |
| 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 | cli-tool/components/skills/scientific/cosmic-database/scripts/download_cosmic.py:24 | |
| MEDIUM | Network egress to untrusted endpoints HTTP request to raw IP address 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 | cli-tool/components/mcps/devtools/figma-dev-mode.json:4 | |
| MEDIUM | Unpinned Dependencies in Installation Instructions The installation instructions recommend installing Python packages (`requests`, `pandas`) without specifying exact versions. This practice can lead to supply chain risks, as future versions of these packages might introduce breaking changes, unexpected behavior, or even security vulnerabilities. It also makes the skill's environment less reproducible. Pin dependency versions to ensure reproducibility and mitigate risks from unexpected updates. For example, `uv pip install requests==2.28.1 pandas==1.5.3`. Regularly review and update pinned versions. | Static | SKILL.md:30 | |
| LOW | Covert behavior / concealment directives Multiple zero-width characters (stealth text) Remove hidden instructions, zero-width characters, and bidirectional overrides. Skill instructions should be fully visible and transparent to users. | Manifest | cli-tool/components/mcps/devtools/jfrog.json:4 |
Scan History
Embed Code
[](https://skillshield.io/report/51db00240f56f3a5)
Powered by SkillShield