Trust Assessment
financial-calculator received a trust score of 85/100, 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 Unpinned dependency in documentation, Unpinned dependency in installation script, Information disclosure via generic exception handling.
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 13, 2026 (commit 13146e6a). 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 | Unpinned dependency in documentation The `flask` dependency is mentioned in the `SKILL.md` documentation for installation without a specific version constraint. This makes the skill vulnerable to supply chain attacks if a malicious or vulnerable version of `flask` is published to PyPI. Users following these instructions could unknowingly install compromised software. Pin the dependency to a specific, known-good version (e.g., `flask==2.3.3`) or instruct users to install from a `requirements.txt` file with pinned versions. | LLM | SKILL.md:120 | |
| MEDIUM | Unpinned dependency in installation script The `flask` dependency is installed without a specific version constraint in the `launch_ui.sh` script. This makes the skill vulnerable to supply chain attacks if a malicious or vulnerable version of `flask` is published to PyPI. When the script is run, it could unknowingly install compromised software. Pin the dependency to a specific, known-good version (e.g., `flask==2.3.3`) or use a `requirements.txt` file with pinned versions. | LLM | scripts/launch_ui.sh:13 | |
| LOW | Information disclosure via generic exception handling The `web_ui.py` script uses a broad `except Exception as e:` block and returns `str(e)` directly in API responses. This can lead to information disclosure, potentially exposing internal server details, file paths, or stack traces to an attacker if an unexpected error occurs. While not a direct exploit, this information can aid in further reconnaissance and attack planning. Implement more specific exception handling. For production environments, avoid returning raw exception messages to clients. Instead, log the detailed error internally and return a generic, user-friendly error message. | LLM | scripts/web_ui.py:33 |
Scan History
Embed Code
[](https://skillshield.io/report/6974298dc9605d25)
Powered by SkillShield