The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external data from hosts and JSON files, creating an ingestion surface for potential indirect prompt injection attacks.- Ingestion points: Data is fetched from remote hosts via utils/export_module, utils/import_module, and postgrestRequest (SKILL.md Stages 2, 4, and 5).- Boundary markers: The instructions do not specify the use of delimiters or safety wrappers for record content or CLI error messages.- Capability inventory: The skill possesses file system access (read/write JSON files), network access (via semantius CLI targeting remote hosts), and shell command execution.- Sanitization: No explicit sanitization or filtering of external content is mandated before data or error output is presented to the user or used by the agent.

semantius-transfer