The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted data from external review reports which may contain instructions designed to manipulate the synthesis logic.\n
Ingestion points: Reads review files from the reviews/ directory and comment-tracker.md in the project structure.\n
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are used when parsing input files.\n
Capability inventory: The skill utilizes Read, Write, Edit, Glob, and Grep tools. It does not have access to tools for network communication or arbitrary code execution.\n
Sanitization: No specific sanitization, filtering, or validation of the text content extracted from the reports is described in the workflow.

synthesise-reviews