The Agent Skills Directory

[COMMAND_EXECUTION]: The helper script scripts/agent.py uses the subprocess module to execute forensic analysis tools such as Volatility 3, rkhunter, and chkrootkit to inspect memory dumps and system integrity.
[DYNAMIC_EXECUTION]: The workflow in SKILL.md utilizes a shell heredoc to dynamically generate and execute a Python script that compares process lists for discrepancies during cross-view analysis.
[INDIRECT_PROMPT_INJECTION]: The skill processes output from forensic tools which analyze potentially compromised systems, creating a surface for indirect prompt injection if a rootkit attempts to manipulate tool output with malicious instructions.
Ingestion points: The skill ingests process IDs and module information from tool outputs like pslist_output.txt and memory dumps in both scripts/agent.py and SKILL.md.
Boundary markers: No delimiters or safety instructions are used to separate tool output from the agent's control logic.
Capability inventory: The agent can execute shell commands via subprocess.run, perform file reads/writes, and list directory contents.
Sanitization: There is no evidence of sanitization or validation of the data retrieved from the forensic tools before it is processed.

detecting-rootkit-activity