The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill reads and processes existing project files which could contain malicious instructions designed to influence the agent's behavior.
Ingestion points: The instructions in SKILL.md direct the agent to 'Check out the current project state first (files, docs, recent commits)' to understand the project context.
Boundary markers: The skill lacks explicit instructions or delimiters to treat ingested content as data rather than instructions, potentially leading the agent to follow directions found within project files.
Capability inventory: The skill possesses the capability to write design documents to the file system (docs/plans/), perform git commits, and delegate worktree operations to external skills.
Sanitization: There are no documented steps for sanitizing, validating, or filtering the content retrieved from the project context.
[COMMAND_EXECUTION]: The skill performs standard development environment operations.
Evidence: SKILL.md instructs the agent to 'Commit the design document to git' and delegate worktree management to the worktree-manager skill.

brainstorming