The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external auction edicts and lot descriptions provided by users, which could contain malicious instructions.
Ingestion points: User-supplied lot/edict data as described in the analysis workflows in SKILL.md.
Boundary markers: The skill does not define specific delimiters or instructions to treat user data as untrusted content.
Capability inventory: The skill ecosystem includes local Python scripts for orchestration and file system writes in scripts/governance.py.
Sanitization: No evidence of input sanitization or filtering is present in the provided files.
[COMMAND_EXECUTION]: The SKILL.md documentation provides commands for the user to execute local scripts using absolute paths (e.g., python C:\Users\renat\skills\agent-orchestrator\scripts\scan_registry.py). This indicates the skill relies on a local environment setup where these scripts manage registry and orchestration tasks.

leiloeiro-ia