skills/flutter/devtools/preparing-pr/Gen Agent Trust Hub

preparing-pr

Pass

Audited by Gen Agent Trust Hub on Oct 31, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute project-specific and standard shell commands to prepare a PR.
  • Commands include: dt update-flutter-sdk, dt presubmit --fix, git status, and git diff.
  • These tools are consistent with the vendor's 'flutter' environment and development workflow.
  • [INDIRECT_PROMPT_INJECTION]: The skill creates a surface where the agent processes potentially untrusted data from the repository.
  • Ingestion points: The agent reads output from git status and git diff to identify modified files and determine which tests to run (SKILL.md).
  • Boundary markers: There are no explicit instructions or delimiters to protect against prompt injection patterns that might be contained within the code diffs being analyzed.
  • Capability inventory: The agent has the capability to execute the dt CLI tool and various test scripts based on the ingested data.
  • Sanitization: No sanitization or validation of the diff content is performed before the agent uses it to decide which commands to execute.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 31, 2026, 07:53 AM