The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to the way it processes external data.
Ingestion points: The skill fetches content from arbitrary external event websites using WebFetch as described in Step 3 of SKILL.md.
Boundary markers: There are no explicit instructions or delimiters defined to ensure the agent ignores or sanitizes instructions that might be embedded within the scraped HTML content (e.g., in speaker bios or sponsor descriptions).
Capability inventory: The skill possesses significant capabilities that could be abused if an injection is successful, including searching for people, revealing sensitive contact details like emails and phone numbers, and creating lead lists via the Amplemarket MCP server.
Sanitization: The skill lacks explicit sanitization or validation of the fetched web content before it is processed by the agent.
[EXTERNAL_DOWNLOADS]: The skill performs network operations to retrieve information from the open web.
It uses WebSearch to locate conference URLs and WebFetch to extract the text content from those pages.
This behavior is a core component of the skill's intended lead generation functionality and is used to gather information on speakers, sponsors, and exhibitors.

conference-event-lead-finder