The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the forge-memory CLI for project state management, including operations like search, log, and sync. This tool is a vendor-provided resource associated with the Forge SM agent environment.
[PROMPT_INJECTION]: The skill processes untrusted content from local documentation files, creating an attack surface for indirect prompt injection.
Ingestion points: The skill reads docs/prd.md, docs/architecture.md, and .forge/memory/sessions/ into the agent's context.
Boundary markers: No specific delimiters or instructions are used to differentiate ingested documentation from the agent's primary system instructions.
Capability inventory: The agent can write generated stories to the docs/stories/ directory and interact with the forge-memory memory management tool.
Sanitization: There is no evidence of sanitization or validation of the input documentation contents before they are processed by the agent.

forge-stories