Trust Assessment
api-patterns received a trust score of 48/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 2 findings: 0 critical, 1 high, 1 medium, and 0 low severity. Key findings include Excessive Permissions Declared, Potential Data Exfiltration via File Reading and Output.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. All layers scored 70 or above, reflecting consistent security practices.
Last analyzed on February 20, 2026 (commit e36d6fd3). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Potential Data Exfiltration via File Reading and Output The `api_validator.py` script takes a `project_path` directly from `sys.argv[1]` without sanitization or restriction on the path's scope. It then uses `project_path.glob()` to find files and `file_path.read_text()` to read their contents. The script prints analysis results, including potential error messages that might contain snippets of the file content (e.g., `Parse error: {e}`). If a malicious user provides a `project_path` pointing to sensitive directories (e.g., `/etc`, `~/.ssh`, or a project directory containing credentials), the script could read these files and leak their contents or structural information through its standard output, which the LLM could then exfiltrate. Implement strict validation and sandboxing for the `project_path` argument. Consider restricting the `project_path` to a specific, non-sensitive working directory or using a more robust file access control mechanism. Ensure that error messages or output do not inadvertently expose sensitive file content. If possible, process files in an isolated environment or use a tool that provides content filtering for sensitive data. | Static | scripts/api_validator.py:102 | |
| MEDIUM | Excessive Permissions Declared The skill declares 'Write' and 'Edit' permissions in its manifest, but the provided `api_validator.py` script only performs read and glob operations. The skill's description ('API design principles and decision-making') also does not inherently require modifying files. Granting unnecessary write/edit access increases the attack surface, allowing a potentially compromised agent to alter or delete files. Remove 'Write' and 'Edit' from the 'allowed-tools' in the skill's manifest, as they are not utilized by the provided script or justified by the skill's stated purpose. Only declare permissions strictly necessary for the skill's functionality. | Static | SKILL.md:3 |
Scan History
Embed Code
[](https://skillshield.io/report/4c5992cf4623bf57)
Powered by SkillShield