Trust Assessment
1password received a trust score of 93/100, 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 Data Exfiltration via Command Output Capture.
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 18, 2026 (commit b62bd290). 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 Data Exfiltration via Command Output Capture The skill's example demonstrates the use of `tmux capture-pane` to capture the full output of `op whoami` and `op vault list` commands. These commands can reveal sensitive metadata such as the 1Password account email, account URL, and names of accessible vaults. If the agent or host LLM processes, logs, or stores this captured output without proper redaction or security controls, it could lead to the unintended exposure or exfiltration of this sensitive information. Review how the captured output from `op whoami` and `op vault list` is handled by the agent. Implement mechanisms to redact or filter sensitive information from command outputs before logging or storing them. Alternatively, modify the skill to avoid capturing output from commands that reveal sensitive data if that data is not strictly necessary for the skill's function, or explicitly warn the user about the sensitive nature of the captured output. | Static | SKILL.md:36 |
Scan History
Embed Code
[](https://skillshield.io/report/19b819f08038f08c)
Powered by SkillShield