create-issue
Pass
Audited by Gen Agent Trust Hub on Apr 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use the
ghCLI to create issues and perform API calls. It explicitly suggests usingGIT_SSL_NO_VERIFY=1in sandbox environments, which disables TLS certificate verification. This is a security risk that could allow an attacker to intercept or modify communication between the agent and GitHub. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it ingests untrusted user input to generate GitHub issues.
- Ingestion points: User descriptions and task breakdowns in Step 1.
- Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the issue body templates.
- Capability inventory: The skill has the capability to write to external repositories via
gh issue createandgh apiPOST requests. - Sanitization: No sanitization or validation of the user-provided text is performed before it is passed to the shell commands or API calls.
Audit Metadata