The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill uses WebSearch and WebFetch to research valuation data and investor lists. If the agent visits a malicious website during this process, embedded instructions could influence the agent's behavior.
Ingestion points: External content retrieved via WebFetch and startup-specific documents in the founder/ directory (facts.md, metrics-dashboard.md, etc.).
Boundary markers: The skill does not define explicit delimiters or instructions to ignore commands within processed data.
Capability inventory: The agent has permissions to Read, Edit (scoped to founder/**), WebSearch, and WebFetch.
Sanitization: No sanitization logic or content filtering is described for handling external web content before it enters the context.

fundraise-prep