review-gha-migration

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions require the agent to execute vendor CLI tools (rwx docs pull, rwx docs search, rwx lint) via bash to retrieve migration guides and perform linting. These are primary functions of the skill provided by the vendor.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided YAML workflows which introduces a risk of indirect prompt injection.
  • Ingestion points: The agent reads the full content of GitHub Actions and RWX configuration files during Step 1 and Step 2.
  • Boundary markers: There are no instructions to use specific delimiters or to ignore potential instructions embedded within the CI files.
  • Capability inventory: The agent has access to the bash tool, which could be misused if instructions in the files were followed.
  • Sanitization: The skill processes the configuration content without any explicit validation or sanitization routines.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 03:05 PM
Security Audit — agent-trust-hub — review-gha-migration