The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes untrusted text from multiple sources which creates an indirect prompt injection surface. Ingestion points: git diff output, .md, .html, and .txt files, and user-pasted messages. Boundary markers: The instructions lack delimiters or isolation markers to separate external content from system instructions. Capability inventory: The skill uses Bash, Read, Grep, and Glob tools to access and process files. Sanitization: There is no evidence of sanitization or filtering for the ingested data.
[COMMAND_EXECUTION]: The skill uses the Bash tool to execute git diff commands using branch names and file ranges provided by the user. This creates a command injection surface if the agent fails to properly sanitize or escape these inputs before they are passed to the shell.

reviewer-en