Trust Assessment
opsgenie 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 Unsanitized Placeholder.
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 Unsanitized Placeholder The skill provides a `curl` command template for acknowledging alerts that includes a placeholder `{alertId}`. If an LLM substitutes this placeholder directly with unsanitized user input and executes the command in a shell, a malicious user could inject arbitrary shell commands. For example, providing `123/foo; rm -rf /` as `alertId` could lead to arbitrary command execution if the LLM does not properly sanitize or escape the input before execution. Implement robust input sanitization and validation for all user-provided parameters before constructing and executing shell commands. Ensure that placeholders like `{alertId}` are properly escaped or validated to prevent shell metacharacter injection. If possible, use an API client library that handles URL encoding and parameter passing securely instead of direct shell execution of `curl` commands. | LLM | SKILL.md:20 |
Scan History
Embed Code
[](https://skillshield.io/report/a2fadd73a6807182)
Powered by SkillShield