github-ops
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from GitHub issues, pull requests, and CI logs. It incorporates robust defensive instructions that mandate the agent treat this content strictly as data, ignore embedded directives like 'ignore previous rules', and seek user confirmation before performing any actions based on external text. Evidence includes ingestion via gh CLI and specific warnings against following reproduction steps from bug reports.
- [COMMAND_EXECUTION]: The skill utilizes the GitHub CLI (gh) and git for standard administrative tasks including triaging issues, reviewing pull requests, and managing release tags. All commands are standard for repository operations.
- [DYNAMIC_EXECUTION]: The release workflow involves running local verification scripts via Node.js and performing package validation using npx. These operations are part of a documented and controlled release process for the repository.
Audit Metadata