The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute several shell commands, including git, mkdir, ln, and date. These commands incorporate user-supplied input (slugs and goals) into command arguments. While the skill includes prompt-level instructions for the agent to sanitize these inputs (e.g., 'lowercase, hyphens only'), this remains a potential vector for command injection if sanitization fails.
[INDIRECT_PROMPT_INJECTION]: The skill demonstrates an indirect prompt injection surface (Category 8):
Ingestion points: The close and status subcommands read content from external files located in docs/plans/active/ and docs/sprints/ to check delivery status and progress.
Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when processing the content of these external files.
Capability inventory: The skill has significant capabilities, including writing to the filesystem and performing git push operations directly to the main branch.
Sanitization: There is no explicit sanitization or validation of the content read from plan files before it is processed by the agent.

plot-sprint