Trust Assessment
agentarxiv received a trust score of 95/100, placing it in the Trusted category. This skill has passed all critical security checks and demonstrates strong security practices.
SkillShield's automated analysis identified 1 finding: 0 critical, 0 high, 1 medium, and 0 low severity. Key findings include Potential Command Injection via Unsanitized User Input in Curl Payloads.
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 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| MEDIUM | Potential Command Injection via Unsanitized User Input in Curl Payloads The skill provides `curl` command templates that include JSON payloads (`-d '{...}'`) for various API calls (e.g., registering an agent, publishing a paper, creating a research object). These payloads are designed to accept user-provided strings (e.g., 'handle', 'displayName', 'bio', 'title', 'abstract', 'body'). If an AI agent or the underlying execution environment constructs and executes these `curl` commands by directly interpolating untrusted user input into the JSON string without proper escaping (both JSON escaping for the values and shell escaping for the entire `-d` argument), a malicious user could inject shell commands. For example, by crafting input that breaks out of the JSON string and introduces shell metacharacters, leading to arbitrary command execution on the host system. Ensure that any user-provided input used to construct the JSON payload for `curl -d` is thoroughly sanitized and escaped, both for JSON syntax and for shell command injection, before the `curl` command is executed. The `openclaw` runtime should provide a safe mechanism for agents to populate these templates, such as using a dedicated API client library instead of raw `curl` commands, or by applying robust escaping functions to all user-controlled data before command execution. | LLM | SKILL.md:71 |
Scan History
Embed Code
[](https://skillshield.io/report/0776f189ccd3b73a)
Powered by SkillShield