The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to process content from various untrusted external sources, which creates a potential surface for indirect prompt injection.
Ingestion points: The skill retrieves data from official sites, registries, professional profiles, directories, and public filings as specified in the references/prospecting-system.md file.
Boundary markers: The provided instructions do not include boundary markers or delimiters to separate untrusted external content from the agent's instructions, nor do they include warnings to ignore embedded instructions in retrieved data.
Capability inventory: The skill is intended to perform lead research and manage email sequences, which involves the use of tools for web navigation and communication.
Sanitization: No mechanisms for sanitizing or validating external content before processing are described in the skill files.

outbound-prospecting