Trust Assessment
omi-me received a trust score of 81/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 2 findings: 0 critical, 1 high, 1 medium, and 0 low severity. Key findings include Execution of unprovided external scripts/binaries, API token printed to standard output.
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 Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Execution of unprovided external scripts/binaries The skill requires and instructs the execution of external scripts (`setup.sh`, `omi-token.sh`) and binaries (`omi`) whose source code is not provided within the skill package. This introduces a significant supply chain risk as the executed code is opaque and could contain malicious functionality. The `setup.sh` script is explicitly called, and all `omi` and `omi-token.sh` commands rely on unverified external code. Provide the source code for all required scripts and binaries within the skill package, or link to a trusted, version-controlled repository. Implement sandboxing for external commands to limit their capabilities. | LLM | SKILL.md:30 | |
| MEDIUM | API token printed to standard output The skill explicitly documents commands (`omi-token.sh get`, `cat ~/.config/omi-me/token`) that print the sensitive Omi.me API token to standard output. If an LLM executes these commands and its output is not properly sanitized or contained, the API token could be captured and exfiltrated, leading to unauthorized access to the Omi.me account. Avoid printing sensitive credentials to stdout. Implement secure methods for token retrieval that do not expose the raw token, or ensure that the environment executing the skill has robust output sanitization and exfiltration prevention mechanisms. | LLM | SKILL.md:60 |
Scan History
Embed Code
[](https://skillshield.io/report/b2ea7e2c1704fb46)
Powered by SkillShield