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

push

Pass

Audited by Gen Agent Trust Hub on Sep 26, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • Command Execution: The skill performs local operations using make, mix, git, and the GitHub CLI (gh). These commands are used to validate code quality and manage repository state, which is standard for a development-focused skill.
  • Indirect Prompt Injection Surface: The skill processes data by reading pull request bodies and repository templates.
  • Ingestion points: Content enters the context through gh pr view and the .github/pull_request_template.md file.
  • Boundary markers: There are no explicit delimiters defined for the ingested text in the instructions.
  • Capability inventory: The skill can execute shell commands (make, mix) and interact with remote repositories via git and gh.
  • Sanitization: The skill utilizes mix pr_body.check to validate the integrity and structure of the PR body before updates are finalized.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 26, 2026, 05:48 PM