skills/openai/symphony/push/Gen Agent Trust Hub

push

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • Command Execution via Local Build Tools: The skill executes make -C elixir all and mix pr_body.check. These commands are standard in development environments for validating code quality and checking pull request descriptions before they are finalized.- Integration with External Services: The skill uses the gh CLI and git to interact with GitHub. This involves standard network operations for pushing code changes and managing repository metadata on GitHub's platform.- Indirect Prompt Injection Surface: The skill ingests external data by reading pull request bodies and template files. This content is used to inform the agent's PR updates. While this is a necessary part of the workflow, it represents a surface where the agent processes text from the repository that could contain embedded instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 01:34 AM