The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: Fetches Falco GPG keys and repository configurations from falco.org and falcosecurity.github.io. These are trusted official sources for the project and follow standard security practices for software distribution.
[COMMAND_EXECUTION]: The Python scripts agent.py and process.py execute system commands such as falco, systemctl, and kubectl to manage the security environment. These calls are implemented securely using argument lists in subprocess.run and are essential for the skill's logic.
[INDIRECT_PROMPT_INJECTION]:
Ingestion points: Alert log file paths processed in scripts/agent.py and scripts/process.py.
Boundary markers: Absent; the scripts do not use specific markers to delimit log data.
Capability inventory: Includes subprocess calls for system status, rule validation, and deployment in both scripts/agent.py and scripts/process.py.
Sanitization: Absent; the scripts perform JSON decoding but do not sanitize the content of log fields.

detecting-container-escape-with-falco-rules