Trust Assessment
ask-a-human received a trust score of 86/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Potential Command Injection via 'exec' with User Input.
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 Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Potential Command Injection via 'exec' with User Input The skill explicitly instructs the AI agent to use the `exec` tool to make API calls, providing `curl` examples. These examples include a `prompt` field within the JSON payload that is intended to contain 'Your question with full context'. If the AI agent constructs the `curl` command by directly interpolating user-controlled input (e.g., from the `prompt` field) into the shell command string without proper escaping, it creates a command injection vulnerability. An attacker could craft malicious input in the `prompt` that breaks out of the JSON string and executes arbitrary shell commands on the host system via the `exec` tool. When constructing shell commands that include user-controlled data, especially within JSON payloads, ensure that all user input is properly escaped. It is highly recommended to use a robust HTTP client library (if available to the agent) instead of direct `exec` calls with `curl` for API interactions. If `exec` must be used, the JSON payload should be constructed using a dedicated JSON library and then passed as a single, properly quoted argument to `curl -d` to prevent shell injection. The agent should also validate and sanitize any input before incorporating it into commands. | LLM | SKILL.md:50 |
Scan History
Embed Code
[](https://skillshield.io/report/9d4e3f27c235352e)
Powered by SkillShield