The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted roadmap data from local documentation files and provides instructions to rewrite this data. While primarily a text-processing task, the absence of boundary markers or sanitization steps means instructions embedded within a roadmap could potentially influence the agent's behavior during the transformation process.\n
Ingestion points: The skill reads roadmap information from documentation paths including docs/plans/** and docs/requirements/**.\n
Boundary markers: The instructions do not define specific delimiters or separators to isolate user-provided roadmap text from the transformation logic.\n
Capability inventory: The skill utilizes Read and Write tools, enabling it to both access and modify project documentation.\n
Sanitization: There are no explicit steps provided to escape, validate, or filter the external roadmap content before it is processed by the model.

outcome-roadmap