The Agent Skills Directory

[COMMAND_EXECUTION]: The Python scripts 'scripts/agent.py' and 'scripts/process.py' execute a wide range of system commands using the subprocess module to gather forensic data. This is documented and essential for the tool's primary purpose.\n- [DATA_EXFILTRATION]: The skill collects sensitive information such as environment variables, system logs, and registry keys. While this involves high-privilege data access, it is consistent with the skill's forensic collection workflow and no external exfiltration was identified.\n- [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface as it processes untrusted system data from process lists and network connections. Ingestion points: scripts/agent.py and scripts/process.py. Boundary markers: Absent. Capability inventory: Subprocess calls in scripts/agent.py and scripts/process.py. Sanitization: Absent. The risk is low as the data is collected for storage and manual forensic review rather than being used for automated agent logic.

collecting-volatile-evidence-from-compromised-host