review-synthesis
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions specify running the command
git status --shortto understand the repository state prior to starting a review. This is a benign operation standard for development-oriented agents. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external repository content and documentation, which constitutes a potential surface for indirect prompt injection.
- Ingestion points: Target files, repository instructions, documentation, and
git statusoutput as defined in the workflow steps in SKILL.md. - Boundary markers: The instructions do not explicitly require the use of delimiters or specific markers when processing external file content.
- Capability inventory: The skill utilizes file system read access and the ability to spawn subagents to perform delegated review tasks.
- Sanitization: No explicit sanitization or filtering logic is prescribed for the content being reviewed; however, the synthesis process includes manual verification of subagent claims and consensus building.
Audit Metadata