The Agent Skills Directory

[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to its core functionality of reading and processing external data (source code files).
Ingestion points: The skill uses tools like Read, Grep, and Glob to ingest content from .ts, .tsx, .js, and .jsx files triggered by project activity.
Boundary markers: The instructions lack explicit delimitation or directives for the agent to ignore potential commands embedded within code comments or string literals in the analyzed files.
Capability inventory: The skill is granted Edit and Write capabilities, meaning a successful injection could lead to unauthorized file modifications.
Sanitization: No sanitization or input validation logic is present to filter out malicious instructions hidden within processed files.

typescript-expert