The Agent Skills Directory

[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface.
Ingestion points: The agent is directed to read untrusted content from memory/claim-board.md, memory/evidence-board.md, and project-specific files.
Boundary markers: No delimiters or specific warnings are provided to the agent to treat ingested data as non-instructional content.
Capability inventory: The skill allows the agent to use Bash for computations and Write or Edit for updating claims based on the processed data.
Sanitization: There is no requirement for the agent to sanitize or validate the content of the files before using them in its workflow.

statistical-analysis-planner