Trust Assessment
aubrai-longevity 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 Command Injection via Untrusted API Response (Request ID).
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 Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Command Injection via Untrusted API Response (Request ID) The skill instructs the host LLM to save `requestId` from an external API response and then directly interpolates this value into a subsequent shell command's URL path. Specifically, the command `curl -sS "https://api.aubr.ai/api/chat/status/${REQUEST_ID}"` is vulnerable. If the external API (`api.aubr.ai`) is compromised or malicious, it could return a `requestId` containing shell metacharacters (e.g., `123; rm -rf /;`). When the LLM substitutes this value, it could lead to arbitrary command execution on the host system, as the shell would interpret the malicious characters as separate commands. The host LLM must sanitize or properly shell-escape any variables derived from untrusted external API responses (like `requestId`) before interpolating them into shell commands. A more robust solution would be to use a dedicated HTTP client library that handles URL construction and parameter passing securely, rather than constructing shell commands via direct string interpolation. | LLM | SKILL.md:20 |
Scan History
Embed Code
[](https://skillshield.io/report/c0a438a077697a40)
Powered by SkillShield