flutter-review-request

Pass

Audited by Gen Agent Trust Hub on Sep 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes standard shell commands (git rev-parse) to retrieve commit identifiers (SHAs). These are used to define the range of code changes to be reviewed by the subagent.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process code changes from the repository, which is a surface for indirect prompt injection if the code being reviewed contains malicious instructions.
  • Ingestion points: Commit SHAs and file contents passed to the Task tool for review.
  • Boundary markers: None identified in the provided prompt template.
  • Capability inventory: Dispatches a subagent (flutter-craft:flutter-code-reviewer) using the Task tool.
  • Sanitization: No explicit sanitization or filtering of the code content is mentioned before dispatching to the subagent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 27, 2026, 11:51 AM