The Agent Skills Directory

[PROMPT_INJECTION]: The skill presents an indirect prompt injection surface. It ingests untrusted data from external sources via WebSearch and WebFetch, as well as codebase content via Grep, Glob, and Read. It lacks boundary markers to delimit external content and does not provide instructions to ignore embedded commands. The skill's capabilities include shell command execution (Bash), file system modification (Write), and task orchestration (Task), which could be misused if malicious instructions are encountered in processed data. No sanitization or filtering of external content is specified.
[COMMAND_EXECUTION]: The skill utilizes the Bash tool to perform directory management, specifically executing mkdir -p docs/research to ensure the output directory exists.
[EXTERNAL_DOWNLOADS]: The skill performs network operations using WebSearch and WebFetch to retrieve technical documentation and information from the public internet.

research