The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes a local Python script scripts/check-output.py to validate the structural integrity of the generated meeting briefs.
[PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it processes external research data. Ingestion points: External account research and attendee profiles collected during Phases 1 and 2 in SKILL.md. Boundary markers: No specific delimiters or safety warnings are included in templates/output-template.md to isolate external data. Capability inventory: File system interaction via the validation script and research tool usage. Sanitization: There is no evidence of sanitization or filtering applied to external content before it is added to the agent's context.
[EXTERNAL_DOWNLOADS]: Includes links to external sales methodology documentation and resources from established platforms like MEDDICC.com, Amazon, and SalesGrowth.com, which are well-known and safe context providers.

meeting-prep