The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a local Python script located at ./.trellis/scripts/get_context.py using python3. This script is used to manage task state and retrieve workflow instructions.
[INDIRECT_PROMPT_INJECTION]: The skill processes project-specific data which serves as a potential attack surface for indirect prompt injection.
Ingestion points: Data is ingested from prd.md, implement.jsonl, and .trellis/workflow.md when determining the current task status and next steps.
Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore potentially malicious embedded content within these files.
Capability inventory: The skill has the capability to execute shell commands (python3) based on the routing logic determined from the ingested files.
Sanitization: The skill does not describe any validation or sanitization of the contents within prd.md or implement.jsonl before processing them.

trellis-continue