The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests data from external, potentially untrusted sources such as SIEM alerts and external ticketing API responses.
Ingestion points: The alert_data object in SKILL.md and the JSON responses from list_open_incidents() or list_cases() in scripts/agent.py.
Boundary markers: The skill does not use delimiters or explicit instructions to the agent to ignore potentially malicious content embedded within security alerts or incident descriptions.
Capability inventory: The skill possesses network communication capabilities (via the requests library to ServiceNow and TheHive APIs) and file system write access (via the --output argument in scripts/agent.py).
Sanitization: There is no evidence of input validation, escaping, or sanitization of external data before it is interpolated into ticket payloads or written to local reports.
[COMMAND_EXECUTION]: The skill provides a functional Python script, scripts/agent.py, which is intended for command-line execution. This script performs network operations and local file writes based on user-supplied parameters. While this is the intended purpose of the skill, it represents a standard execution surface for the agent.

implementing-ticketing-system-for-incidents