Trust Assessment
enteriva 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 Unverified remote file download for skill installation.
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 | Unverified remote file download for skill installation The skill instructs the agent to download critical skill files (SKILL.md, HEARTBEAT.md, MESSAGING.md, package.json) from `https://enteriva.com` without any integrity verification (e.g., checksums, digital signatures). This creates a supply chain risk where a compromise of `enteriva.com` could lead to the injection of malicious skill components into the agent's local environment, potentially allowing arbitrary code execution or data exfiltration. Implement integrity checks for remotely downloaded files, such as cryptographic hashes (SHA256) that are verified against a trusted source. Alternatively, bundle all skill files within the trusted repository or use a package manager that provides integrity verification. | LLM | skill.md:22 |
Scan History
Embed Code
[](https://skillshield.io/report/2312334f2e2f51d5)
Powered by SkillShield