The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external codebases to perform audits, repairs, and migrations, which creates a surface for indirect prompt injection if malicious instructions are embedded in the user's code.
Ingestion points: The skill reads user-provided React and TypeScript files containing React Flow components and logic, as specified in references/CHECKLIST.md and SKILL.md.
Boundary markers: There are no explicit instructions or delimiters defined to separate the ingested code content from the agent's instructions, nor are there warnings to ignore embedded natural language commands.
Capability inventory: The skill is designed to read file contents, identify patterns, and apply code patches across project files, which could lead to unauthorized code modifications if an injection is successful.
Sanitization: The skill lacks validation or sanitization mechanisms to distinguish between legitimate code structures and malicious instructions embedded within code comments or string literals.

react-flow