Trust Assessment
context7 received a trust score of 65/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 2 findings: 2 critical, 0 high, 0 medium, and 0 low severity. Key findings include Potential Command Injection via unsanitized `curl` parameters.
The analysis covered 4 layers: dependency_graph, manifest_analysis, llm_behavioral_safety, static_code_analysis. The llm_behavioral_safety layer scored lowest at 40/100, indicating areas for improvement.
Last analyzed on February 11, 2026 (commit 326f2466). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Potential Command Injection via unsanitized `curl` parameters The skill documentation provides `curl` commands that include placeholders for `libraryName`, `query`, and `libraryId`. If an AI agent directly interpolates untrusted user input into these parameters without proper shell escaping or validation, a malicious user could inject arbitrary shell commands. For example, by providing `libraryName="; rm -rf /; echo "` as input, an attacker could execute `rm -rf /` on the host system. This is a critical vulnerability as it allows for arbitrary code execution. The AI agent implementing this skill must ensure that all user-provided inputs (`libraryName`, `query`, `libraryId`) are properly shell-escaped before being inserted into the `curl` command string. Using a robust library function for shell escaping (e.g., `shlex.quote` in Python, `shell_exec` with proper escaping in PHP, or similar in other languages) is highly recommended. Alternatively, if the agent has direct API access, it should use a dedicated HTTP client library instead of shelling out to `curl`. | Unknown | SKILL.md:12 | |
| CRITICAL | Potential Command Injection via unsanitized `curl` parameters The skill documentation provides `curl` commands that include placeholders for `libraryId` and `query`. If an AI agent directly interpolates untrusted user input into these parameters without proper shell escaping or validation, a malicious user could inject arbitrary shell commands. For example, by providing `query="; cat /etc/passwd; echo "` as input, an attacker could execute `cat /etc/passwd` on the host system. This is a critical vulnerability as it allows for arbitrary code execution. The AI agent implementing this skill must ensure that all user-provided inputs (`libraryName`, `query`, `libraryId`) are properly shell-escaped before being inserted into the `curl` command string. Using a robust library function for shell escaping (e.g., `shlex.quote` in Python, `shell_exec` with proper escaping in PHP, or similar in other languages) is highly recommended. Alternatively, if the agent has direct API access, it should use a dedicated HTTP client library instead of shelling out to `curl`. | Unknown | SKILL.md:24 |
Scan History
Embed Code
[](https://skillshield.io/report/69f516e5c7464cc3)
Powered by SkillShield