create-issue

Pass

Audited by Gen Agent Trust Hub on May 18, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes gh api commands to create GitHub issues using both GraphQL and REST APIs. These commands correctly use the -f and -F flags, which ensures that user-provided variables like the issue title and body are treated as literal data rather than potentially executable shell arguments.
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it processes untrusted data from the repository to generate its output.
  • Ingestion points: Reads issue templates from .github/ISSUE_TEMPLATE/ and searches existing issues/code via the GitHub CLI.
  • Boundary markers: Absent. The instructions do not specify the use of delimiters or 'ignore' instructions when processing data from the repository.
  • Capability inventory: Shell execution via gh CLI for API interactions (SKILL.md).
  • Sanitization: Content from files and previous issues is incorporated into the new issue draft without explicit sanitization or filtering.
Audit Metadata
Risk Level
SAFE
Analyzed
May 18, 2026, 09:55 PM
Security Audit — agent-trust-hub — create-issue