The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to execute a local script scripts/check.sh. Although this script is intended for validating paper readiness (anonymity, drafting artifacts, mandatory sections), the script file itself is not included in the provided skill package for technical verification.\n- [INDIRECT_PROMPT_INJECTION]: The skill reads and analyzes LaTeX files provided by the user, which may contain instructions that could be interpreted by the agent.\n
Ingestion points: Project files such as main.tex, venue_preamble.tex, and bibliography files.\n
Boundary markers: No explicit markers are used to separate file data from instructions, allowing untrusted content to influence the agent context.\n
Capability inventory: The skill utilizes Bash, Edit, Read, Glob, and Grep tools, providing a broad range of capabilities if an injection were successful.\n
Sanitization: The instructions do not specify any filtering or sanitization of the file content before processing.

submit-paper