Trust Assessment
senior-frontend received a trust score of 63/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 8 findings: 0 critical, 0 high, 4 medium, and 4 low severity. Key findings include Network egress to untrusted endpoints, Covert behavior / concealment directives, Arbitrary Path Existence Check.
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 11, 2026 (commit 458b1186). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings8
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| 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 | Arbitrary File Overwrite via Output Argument The skill's Python scripts allow writing their JSON output to an arbitrary file path specified by the `--output` argument. Although the current JSON content is limited to benign metadata (status, target path, empty findings), an attacker could use this to overwrite existing files on the system with this content. Overwriting critical system files could lead to denial of service or data corruption. If the `analyze()` method were later implemented to include sensitive data, this would become a more severe data exfiltration or arbitrary file write vulnerability. Restrict the `--output` path to a designated output directory, or ensure that the script only writes to files within its own project scope. Implement checks to prevent overwriting critical system files. | LLM | scripts/bundle_analyzer.py:89 | |
| MEDIUM | Arbitrary File Overwrite via Output Argument The skill's Python scripts allow writing their JSON output to an arbitrary file path specified by the `--output` argument. Although the current JSON content is limited to benign metadata (status, target path, empty findings), an attacker could use this to overwrite existing files on the system with this content. Overwriting critical system files could lead to denial of service or data corruption. If the `analyze()` method were later implemented to include sensitive data, this would become a more severe data exfiltration or arbitrary file write vulnerability. Restrict the `--output` path to a designated output directory, or ensure that the script only writes to files within its own project scope. Implement checks to prevent overwriting critical system files. | LLM | scripts/component_generator.py:89 | |
| MEDIUM | Arbitrary File Overwrite via Output Argument The skill's Python scripts allow writing their JSON output to an arbitrary file path specified by the `--output` argument. Although the current JSON content is limited to benign metadata (status, target path, empty findings), an attacker could use this to overwrite existing files on the system with this content. Overwriting critical system files could lead to denial of service or data corruption. If the `analyze()` method were later implemented to include sensitive data, this would become a more severe data exfiltration or arbitrary file write vulnerability. Restrict the `--output` path to a designated output directory, or ensure that the script only writes to files within its own project scope. Implement checks to prevent overwriting critical system files. | LLM | scripts/frontend_scaffolder.py:89 | |
| 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 | |
| LOW | Arbitrary Path Existence Check The skill's Python scripts accept an arbitrary 'target' path from user input and check its existence using `pathlib.Path.exists()`. This allows an attacker to probe the filesystem for the presence of files or directories, potentially disclosing information about the system's structure or the existence of sensitive resources. While not directly exfiltrating content, this information can be valuable for further attacks. Implement stricter validation for the 'target' path, ensuring it operates only within a designated, sandboxed project directory. Avoid allowing arbitrary filesystem path checks on user-controlled input. | LLM | scripts/bundle_analyzer.py:33 | |
| LOW | Arbitrary Path Existence Check The skill's Python scripts accept an arbitrary 'target' path from user input and check its existence using `pathlib.Path.exists()`. This allows an attacker to probe the filesystem for the presence of files or directories, potentially disclosing information about the system's structure or the existence of sensitive resources. While not directly exfiltrating content, this information can be valuable for further attacks. Implement stricter validation for the 'target' path, ensuring it operates only within a designated, sandboxed project directory. Avoid allowing arbitrary filesystem path checks on user-controlled input. | LLM | scripts/component_generator.py:33 | |
| LOW | Arbitrary Path Existence Check The skill's Python scripts accept an arbitrary 'target' path from user input and check its existence using `pathlib.Path.exists()`. This allows an attacker to probe the filesystem for the presence of files or directories, potentially disclosing information about the system's structure or the existence of sensitive resources. While not directly exfiltrating content, this information can be valuable for further attacks. Implement stricter validation for the 'target' path, ensuring it operates only within a designated, sandboxed project directory. Avoid allowing arbitrary filesystem path checks on user-controlled input. | LLM | scripts/frontend_scaffolder.py:33 |
Scan History
Embed Code
[](https://skillshield.io/report/13a572d22b3a501f)
Powered by SkillShield