Skills
Navigate
skills/remix-run/react-router/release-react-router/Gen Agent Trust Hub

release-react-router

Pass

Audited by Gen Agent Trust Hub on Nov 5, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources, which creates a potential surface for indirect prompt injection.
  • Ingestion points: In SKILL.md, the agent is instructed to read pull request descriptions, diffs, and repository files such as scripts/changes/whats-changed.md from the GitHub repository.
  • Boundary markers: There are no instructions to use delimiters or delimiters to isolate untrusted data from the system prompts or instructions.
  • Capability inventory: The skill leverages powerful tools including gh, git, and npm to perform actions like merging code and verifying publication state.
  • Sanitization: The instructions do not describe any mechanisms for sanitizing or validating the content retrieved from external sources before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 5, 2026, 10:09 AM