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_input field 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
Risk Level
SAFE
Analyzed
Jul 11, 2026, 07:13 AM
Security Audit — agent-trust-hub — workflow-integration-github