Trust Assessment
senior-fullstack received a trust score of 84/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 3 findings: 0 critical, 0 high, 2 medium, and 1 low severity. Key findings include Network egress to untrusted endpoints, Covert behavior / concealment directives, Arbitrary File Write via --output argument.
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 Findings3
| 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 Write via --output argument The Python scripts `scripts/code_quality_analyzer.py`, `scripts/fullstack_scaffolder.py`, and `scripts/project_scaffolder.py` all accept an `--output` argument. This argument allows the script's JSON results to be written to an arbitrary file path specified by the user. While the current output (status, target path, empty findings) is benign, this capability could be abused. If the `analyze` method were to be modified in the future to include sensitive information, this mechanism could lead to data exfiltration. Additionally, an attacker could specify a sensitive system file path (e.g., `/etc/passwd`, `~/.bashrc`) to overwrite it with the script's output, potentially causing denial of service or system instability. 1. **Restrict Output Paths**: Limit output files to a designated, sandboxed directory. 2. **Sanitize Output Paths**: Implement robust checks to prevent path traversal (`../`) and writing to sensitive system locations. 3. **Future-Proofing**: Ensure that any future implementation of the `analyze` method does not gather sensitive data that could be exfiltrated via this mechanism. Consider removing the `--output` argument if direct file writing to arbitrary locations is not a core requirement. | LLM | scripts/code_quality_analyzer.py, scripts/fullstack_scaffolder.py, scripts/project_scaffolder.py:100 | |
| 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/085a5d4f4b1fd055)
Powered by SkillShield