The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to execute grep and wc commands for counting task statuses within the BACKLOG.md file. These commands are hardcoded to specific patterns and target a local file, posing minimal risk.
[PROMPT_INJECTION]: The skill processes external data from BACKLOG.md, which introduces a surface for indirect prompt injection. \n
Ingestion points: The agent reads the contents of BACKLOG.md during the initialization and status update steps. \n
Boundary markers: There are no explicit delimiters or instructions to ignore potential commands embedded within the backlog items. \n
Capability inventory: The skill allows access to Read, Write, Edit, and Bash tools. \n
Sanitization: No input validation or sanitization is performed on the item descriptions or notes read from the file.

manage-backlog