The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill contains logic to process external JSON data representing compliance registers. While this creates a theoretical surface for indirect prompt injection, the risk is negligible as the skill lacks exploitable capabilities like network access or system command execution.
Ingestion points: The scripts/process.py script reads RoPA and DPIA registers from user-specified file paths provided via command-line arguments.
Boundary markers: The script does not implement specific boundary markers or instructions for the agent to ignore content within the data fields.
Capability inventory: The skill is limited to local file read/write operations for generating reports and standard Python data processing. It does not perform network operations or execute arbitrary shell commands.
Sanitization: Data is parsed using the standard json library, which safely handles structured data.
[COMMAND_EXECUTION]: The skill includes a Python script (scripts/process.py) designed to be executed within the agent's environment. This script is a utility for auditing data integrity and does not perform any suspicious or unauthorized system operations.

ropa-dpia-linkage