The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core function of reading untrusted code files.\n
Ingestion points: Uses Read, Grep, and Glob tools to process content from user-specified project files.\n
Boundary markers: There are no instructions to use delimiters or ignore instructions found within the processed files.\n
Capability inventory: The skill allows the use of the Bash tool, which could be leveraged if an injection attack succeeds.\n
Sanitization: No input validation or sanitization is required for the file content before it is processed.

code-review