Trust Assessment
local-places received a trust score of 10/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 7 findings: 4 critical, 0 high, 1 medium, and 0 low severity. Key findings include Network egress to untrusted endpoints, Unpinned Python dependency version, Hardcoded developer hostname in OpenAPI server URL.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Manifest Analysis layer scored lowest at 0/100, indicating areas for improvement.
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 Findings7
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | 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 | skills/steipete/local-places/SKILL.md:21 | |
| CRITICAL | 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 | skills/steipete/local-places/SKILL.md:25 | |
| CRITICAL | 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 | skills/steipete/local-places/SKILL.md:32 | |
| CRITICAL | 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 | skills/steipete/local-places/SKILL.md:44 | |
| MEDIUM | Unpinned Python dependency version Dependency 'fastapi>=0.110.0' is not pinned to an exact version. Pin Python dependencies with exact versions where feasible. | Dependencies | skills/steipete/local-places/pyproject.toml | |
| INFO | Hardcoded developer hostname in OpenAPI server URL The `OPENAPI_SERVER_URL` in `src/local_places/main.py` defaults to a specific developer's machine hostname (`http://maxims-macbook-air:8000`). If the skill's OpenAPI specification is exposed, this could leak internal network topology or developer machine details. While the skill is intended for local use, hardcoding specific hostnames is generally not a best practice. Replace the hardcoded default hostname with a generic value like `http://localhost:8000` or ensure the `OPENAPI_SERVER_URL` environment variable is always explicitly set in deployment environments. | LLM | src/local_places/main.py:18 | |
| INFO | Logging of full request body on validation errors The `validation_exception_handler` in `src/local_places/main.py` logs the entire request body (`exc.body`) when a validation error occurs. If user requests contain sensitive information (e.g., specific locations, personal queries), this data could be written to logs, potentially leading to data exposure if logs are not adequately secured. Implement redaction or filtering mechanisms for potentially sensitive fields within `exc.body` before logging, or ensure that log files are strictly secured and have appropriate retention policies. | LLM | src/local_places/main.py:33 |
Scan History
Embed Code
[](https://skillshield.io/report/3491b08347c29715)
Powered by SkillShield