skills/flutter/website/validate-pr/Gen Agent Trust Hub

validate-pr

Pass

Audited by Gen Agent Trust Hub on May 8, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local dart run dash_site commands to perform site maintenance tasks such as refreshing excerpts, formatting code, and checking link references. These operations are standard for the Flutter documentation repository's build system.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a process that ingests and validates content from local Markdown files and code snippets, which may include untrusted input from pull requests.
  • Ingestion points: Local Markdown files and code excerpts referenced in SKILL.md.
  • Boundary markers: Absent; there are no specific instructions for the agent to use delimiters or ignore embedded content.
  • Capability inventory: The skill utilizes shell command execution (dart) to process the site content.
  • Sanitization: Content validation and formatting are deferred to the dash_site command-line tool.
Audit Metadata
Risk Level
SAFE
Analyzed
May 8, 2026, 03:16 PM