The Agent Skills Directory

[COMMAND_EXECUTION]: The scripts/agent.py script executes the binwalk utility using subprocess.run to extract components from firmware images. This is a core functional requirement of the skill but involves interaction with the host operating system's command-line tools.
[INDIRECT_PROMPT_INJECTION]: The skill analyzes potentially malicious or attacker-controlled firmware images, creating a surface where instructions embedded in the firmware could attempt to override the agent's safety protocols or logic during the analysis phase.
Ingestion points: The scan_for_credentials and scan_for_vulnerabilities functions in scripts/agent.py read and return snippets of code and configuration from extracted firmware files.
Boundary markers: The analysis output does not utilize clear delimiters or specific instructions to the agent to treat the extracted firmware snippets as data rather than instructions.
Capability inventory: The agent possesses file-writing capabilities (for extraction) and network socket capabilities (via the Modbus tester in SKILL.md).
Sanitization: There is no evidence of sanitization or escaping of the strings extracted from binary files before they are presented to the agent context.

performing-plc-firmware-security-analysis