writing-agent-relay-workflows

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides instructions and examples for executing shell commands via git, gh (GitHub CLI), npm, and node. These are used for repository state validation, dependency management, and workflow automation (e.g., gh pr create).
  • [INDIRECT_PROMPT_INJECTION]: The workflow patterns described facilitate the ingestion of external data, such as step outputs and integration event payloads, which are then interpolated into subsequent agent prompts. The skill mitigates risks associated with this surface by providing validation utilities to sanitize repository and branch names before use in shell commands.
  • [EXTERNAL_DOWNLOADS]: The skill references the installation and use of several Node.js packages (@relayflows/core, @relayflows/cli, @agent-relay/sdk) required to implement and run the workflows described in the documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 01:04 PM
Security Audit — agent-trust-hub — writing-agent-relay-workflows