workflow-integration-github
Pass
Audited by Gen Agent Trust Hub on Jul 11, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the GitHub CLI (
gh) to perform operations like creating pull requests, fetching comments, and monitoring CI status. These commands are executed via subprocesses and are central to the skill's primary purpose. - [PROMPT_INJECTION]: The skill handles untrusted data from GitHub PR comments, creating a potential surface for indirect prompt injection. However, it implements a quarantine strategy where raw comment bodies are stored in a dedicated
raw_inputfield and only promoted to the main context after a validation pass. This design minimizes the risk of the agent accidentally executing instructions contained within comments. - [EXTERNAL_DOWNLOADS]: The skill fetches data and logs from GitHub's official API and repositories. As GitHub is a well-known and trusted service, these operations are considered safe and are required for the skill's functionality.
Audit Metadata