The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data such as podcast outlines and shownotes. Ingestion points: Untrusted data enters the agent context through the 'Pauta e shownotes candidatos' and 'brief' files. Boundary markers: The skill does not implement specific delimiters or instructions to ignore embedded commands in analyzed files. Capability inventory: The agent can read context files and write validation reports. Sanitization: No input sanitization is performed on the analyzed content.
[COMMAND_EXECUTION]: The skill executes framework-specific commands inboundfy-setup and inboundfy-base-validador which are part of the vendor's specialized validation environment.

inboundfy-validador-podcast