The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes numerous commands for running OWASP ZAP scanning scripts (e.g., zap-baseline.py, zap-full-scan.py) via Docker and local shell scripts. These commands are intended for automated security testing.
[INDIRECT_PROMPT_INJECTION]: The skill describes workflows where the agent reads and processes scan results and alerts from external web applications. This presents a potential surface for indirect prompt injection if an attacker controls the scanned target.
Ingestion points: Vulnerability data is ingested via the Python client zap.core.alerts (references/automation-api.md) and through reports generated by the scanning scripts (SKILL.md).
Boundary markers: No explicit delimitation or 'ignore instructions' markers are present in the examples.
Capability inventory: The skill uses shell execution for Docker containers and curl commands (SKILL.md, references/automation-api.md).
Sanitization: The provided code snippets do not demonstrate sanitization or validation of the external scan data.
[EXTERNAL_DOWNLOADS]: The skill references official zaproxy resources, including Docker images (zaproxy/zap-stable) and the Python client library (zaproxy). These are well-known and authoritative security tools.

zap