The Agent Skills Directory

[PROMPT_INJECTION]: The skill establishes a surface for indirect prompt injection by directing the agent to process data from untrusted external sources and local configuration files without specified safety boundaries.\n
Ingestion points: The agent is instructed to read the project file .agents/sales-context.md and scrape speaker or exhibitor lists from external event websites and networking platforms (e.g., Brella, Grip, Bizzabo).\n
Boundary markers: The instructions do not define delimiters or provide directives to ignore potentially malicious instructions embedded within the retrieved data.\n
Capability inventory: The agent is required to use file system access and web browsing/scraping capabilities to gather intelligence on prospects.\n
Sanitization: No mention is made of sanitizing or validating the content retrieved from external sources before it is incorporated into the agent's decision-making or outreach generation.

event-networking