The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests and processes data from external sources including the Claroty API and local CMDB CSV files to generate reports and risk summaries (found in SKILL.md and scripts/agent.py). \n
Ingestion points: Data is retrieved via get_assets, get_vulnerabilities, and load_inventory methods.\n
Boundary markers: The skill does not employ explicit delimiters or instructions to isolate external data from the agent's prompt context.\n
Capability inventory: The skill can perform network requests and write to the local file system.\n
Sanitization: No significant sanitization or validation of the ingested strings is performed before they are presented to the agent or exported.\n- [EXTERNAL_DOWNLOADS]: The skill makes network requests to services.nvd.nist.gov to retrieve vulnerability information (SKILL.md). This targets a well-known and trusted public security database. The skill also requires the installation of the standard requests library.\n- [COMMAND_EXECUTION]: The skill provides a command-line interface via scripts/agent.py and instructions in SKILL.md for executing discovery and validation tasks.

performing-ics-asset-discovery-with-claroty