The Agent Skills Directory

[COMMAND_EXECUTION]: The scripts/agent.py script utilizes subprocess.check_output to execute system utilities certutil and certipy for Active Directory enumeration. These commands are executed using list-based arguments, which is a standard secure practice to mitigate shell injection risks.
[INDIRECT_PROMPT_INJECTION]: The script scripts/process.py ingests and parses external data, creating a surface for indirect prompt injection.
Ingestion points: The load_certipy_output function in scripts/process.py reads JSON output files generated by external tools.
Boundary markers: The script does not employ specific delimiters or instruction-ignore markers to isolate the ingested data within the generated report.
Capability inventory: The script performs file-write operations to save assessment results on the local filesystem.
Sanitization: No data sanitization or validation is performed on the strings extracted from the JSON input before they are interpolated into the final report output.

exploiting-active-directory-certificate-services-esc1