The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute local shell commands using python3 to run the tam_builder.py script. The configuration for this script is dynamically generated based on user input and web research results.
[PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection. Ingestion points: The agent ingests user-provided company URLs, product descriptions, and the results of web research tools in Phase 0 and Phase 1. Boundary markers: There are no explicit instructions or delimiters used to prevent instructions embedded within the researched web content from overriding the agent's logic. Capability inventory: The agent has the capability to execute shell commands and send data to multiple external lead-generation and database APIs. Sanitization: The skill lacks instructions to sanitize or validate the external content before it is used to populate search filters or parameters for the downstream tam_builder.py execution.

icp-identification