react-flow

Pass

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (LOW): The skill possesses an indirect prompt injection surface due to its analysis and modification of project files.
  • Ingestion points: The skill reads local project files, including TypeScript and JavaScript source code, as part of its discovery workflow (SKILL.md).
  • Boundary markers: There are no instructions in the protocol to use delimiters or ignore instructions embedded in the analyzed code.
  • Capability inventory: The skill allows the agent to modify source code, apply patches, and generate new scaffolded files (SKILL.md).
  • Sanitization: No sanitization or validation of the input source code is specified to filter out potential embedded instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 18, 2026, 09:11 AM