The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a shell command (ls) within the YAML frontmatter's context field to retrieve a list of existing sprint files from the production/sprints/ directory.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to its reliance on external data sources for generating sprint plans.
Ingestion points: Reads content from production/milestones/, production/sprints/, design/gdd/, and production/risk-register/.
Boundary markers: The instructions do not define delimiters or provide 'ignore embedded instructions' warnings for the data ingested from these files.
Capability inventory: The skill is granted Write and Edit tools, meaning an attacker who can modify design docs or risk registers could potentially trick the agent into performing unauthorized file modifications.
Sanitization: No input validation or filtering is performed on the content retrieved from the file system before it is processed by the agent.

sprint-plan