The Agent Skills Directory

[PROMPT_INJECTION]: The skill ingests data from external research and existing repository files to synthesize implementation plans. This introduces a surface for indirect prompt injection, where instructions embedded in external sources or project files could influence the generated output. • Ingestion points: External research results, subagent responses, and repository-resident planning files. • Boundary markers: The skill lacks explicit delimiters or instructions to isolate untrusted inputs during the synthesis process. • Capability inventory: The skill can write to the filesystem in restricted directories (.plans/ and .reviews/) and delegate tasks to subagents. • Sanitization: No sanitization of external data is specified before its inclusion in the plan drafting phase.

create-plan