The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses dynamic context injection in the YAML frontmatter (!ls production/sprints/ 2>/dev/null) to gather a list of existing sprint files when the skill is loaded. The command is a standard shell utility used for project context without incorporating external or user-supplied variables.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes external data from various project files.
Ingestion points: Phase 1 and Phase 3 involve reading content from production/milestones/, production/sprints/, design/gdd/, and production/risk-register/ as defined in SKILL.md.
Boundary markers: There are no explicit delimiters or instructions provided to the agent to disregard malicious directives that might be embedded within these ingested documents.
Capability inventory: The skill has access to the Write, Edit, and Task tools, which allow for modifying the filesystem and spawning sub-agents.
Sanitization: The skill does not implement any validation or sanitization of the content retrieved from the external files before it is processed by the LLM.
Mitigation: The skill requires explicit user confirmation via AskUserQuestion before performing any write operations to the filesystem in Phase 4 and Phase 5.

sprint-plan