The Agent Skills Directory

[Indirect Prompt Injection] (HIGH): The skill defines a process for reading and analyzing untrusted external content (frontend code), creating a significant attack surface for indirect injection via malicious code comments.
Ingestion points: Processes .tsx, .ts, and .js files from the filesystem (staged changes or specific file paths).
Boundary markers: None. There are no instructions to use delimiters or to disregard instructions found within the code being analyzed.
Capability inventory: The agent can suggest and potentially apply fixes ('Would you like me to use the Suggested fix section to address these issues?'), which allows an injector to influence file modifications.
Sanitization: No sanitization or filtering logic is present to prevent the agent from obeying embedded instructions in the analyzed files.

frontend-code-review