Trust Assessment
serpapi received a trust score of 88/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 2 findings: 0 critical, 0 high, 2 medium, and 0 low severity. Key findings include Suspicious import: urllib.request, Broad file access for configuration reading.
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 14, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| MEDIUM | Suspicious import: urllib.request Import of 'urllib.request' detected. This module provides network or low-level system access. Verify this import is necessary. Network and system modules in skill code may indicate data exfiltration. | Static | skills/ianpcook/serpapi/scripts/serp.py:27 | |
| MEDIUM | Broad file access for configuration reading The `get_default_location` function attempts to read `TOOLS.md` from potentially broad locations, including the current working directory (`Path.cwd() / "TOOLS.md"`) and a specific path within the user's home directory (`Path.home() / "clawd" / "TOOLS.md"`). While the function uses a regular expression to extract a specific 'Default location' value, reading arbitrary files from these directories without explicit user consent or a more restricted scope could be considered an excessive permission. If `TOOLS.md` contains other sensitive information not intended for this skill, or if the regex were less specific, this could lead to data exfiltration. 1. Restrict file access: Limit `TOOLS.md` lookup to only the skill's own directory or the `CLAWDBOT_WORKSPACE` environment variable, which is typically controlled by the agent runtime and provides a more controlled scope. 2. Explicit configuration: Allow the user to explicitly provide the path to their `TOOLS.md` or the default location via an argument or a more specific environment variable, rather than implicitly searching broad paths. 3. Clarify documentation: Clearly state in the skill's documentation that it will attempt to read `TOOLS.md` from these specific locations and what information it expects to find. | LLM | scripts/serp.py:50 |
Scan History
Embed Code
[](https://skillshield.io/report/e7f507c726268808)
Powered by SkillShield