Trust Assessment
senior-secops received a trust score of 71/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 5 findings: 0 critical, 0 high, 4 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 12, 2026 (commit 458b1186). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings5
| 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 `compliance_checker.py`, `security_scanner.py`, and `vulnerability_assessor.py` allow writing their JSON output to an arbitrary file path specified by the `--output` argument. While the content written is currently limited to a hardcoded status, the target path string, and an empty findings list, the capability to write to any file on the system (given appropriate permissions) can lead to denial of service (e.g., overwriting critical files, filling disk space) or could be leveraged in conjunction with other vulnerabilities. If the `analyze` method were to be implemented to include sensitive data from the `target_path` in the `results`, this would become a data exfiltration vector. Restrict the `--output` argument to only allow writing within a designated, sandboxed output directory. Alternatively, implement strict validation for the output path to prevent writing to sensitive system locations or outside a specified project directory. Ensure that any data written to user-specified paths is non-sensitive and cannot be used for further attacks. | LLM | scripts/compliance_checker.py:109 | |
| MEDIUM | Arbitrary File Write via Output Argument The Python scripts `compliance_checker.py`, `security_scanner.py`, and `vulnerability_assessor.py` allow writing their JSON output to an arbitrary file path specified by the `--output` argument. While the content written is currently limited to a hardcoded status, the target path string, and an empty findings list, the capability to write to any file on the system (given appropriate permissions) can lead to denial of service (e.g., overwriting critical files, filling disk space) or could be leveraged in conjunction with other vulnerabilities. If the `analyze` method were to be implemented to include sensitive data from the `target_path` in the `results`, this would become a data exfiltration vector. Restrict the `--output` argument to only allow writing within a designated, sandboxed output directory. Alternatively, implement strict validation for the output path to prevent writing to sensitive system locations or outside a specified project directory. Ensure that any data written to user-specified paths is non-sensitive and cannot be used for further attacks. | LLM | scripts/security_scanner.py:109 | |
| MEDIUM | Arbitrary File Write via Output Argument The Python scripts `compliance_checker.py`, `security_scanner.py`, and `vulnerability_assessor.py` allow writing their JSON output to an arbitrary file path specified by the `--output` argument. While the content written is currently limited to a hardcoded status, the target path string, and an empty findings list, the capability to write to any file on the system (given appropriate permissions) can lead to denial of service (e.g., overwriting critical files, filling disk space) or could be leveraged in conjunction with other vulnerabilities. If the `analyze` method were to be implemented to include sensitive data from the `target_path` in the `results`, this would become a data exfiltration vector. Restrict the `--output` argument to only allow writing within a designated, sandboxed output directory. Alternatively, implement strict validation for the output path to prevent writing to sensitive system locations or outside a specified project directory. Ensure that any data written to user-specified paths is non-sensitive and cannot be used for further attacks. | LLM | scripts/vulnerability_assessor.py:109 | |
| 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/764eff54ab24a3e1)
Powered by SkillShield