re0-merge
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill describes a workflow for processing untrusted external contributions (Pull Requests), which inherently involves an attack surface for indirect prompt injection.
- Ingestion points: External code and documentation from pull requests are evaluated during the review process (SKILL.md).
- Boundary markers: The instructions suggest a 'cold-read' and 'shower' pass to verify claims, though no technical delimiters are implemented in this instructional file.
- Capability inventory: The process involves executing suite-specific tools (re0-git, re0-upgrade, re0-release) and editing core configuration files (plugin.json, scripts/catalog.cjs).
- Sanitization: The workflow mandates rigorous verification, including regression testing of provided fixes and checking against the project's core thesis.
- [NO_CODE]: The skill is a documentation-only asset containing procedural instructions and metadata. It does not provide or execute any scripts, binaries, or shell commands.
Audit Metadata