The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources such as briefs (04-briefs/) and context files (context/marca-voz.md, context/publico.md, etc.) to produce blog articles. This creates a surface where malicious instructions embedded in a brief could potentially influence the agent's behavior during the writing or validation phases.\n
Ingestion points: The agent processes content from files in the 04-briefs/ directory and various Markdown files in the context/ directory.\n
Boundary markers: The skill instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when processing these external data sources.\n
Capability inventory: The skill possesses capabilities to write files to the project's output directory (97-ativos-finais/) and to invoke multiple other skills in the pipeline, such as inboundfy-validador-blog, inboundfy-copy-editor, and inboundfy-base-seo.\n
Sanitization: There is no mention of sanitization, escaping, or validation of the ingested external content before it is interpolated into the workflow.

inboundfy-especialista-blog