The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided text for 'Federation strategic context' and 'MA strategic context' to populate generated reports. This creates a potential surface for indirect prompt injection where instructions hidden in the context data could influence the agent's behavior.
Ingestion points: User-supplied context and question lists defined in the 'Required inputs' section of SKILL.md.
Boundary markers: The skill does not define specific delimiters (e.g., XML tags or triple quotes) or 'ignore embedded instructions' warnings when interpolating user data into the document sub-prompts.
Capability inventory: The skill has the ability to write files to the local environment using the ane_package.reporting module (specifically word_export.write_word_report and pdf_export.write_pdf_report).
Sanitization: No explicit sanitization, escaping, or filtering of the user-provided context is described before it is rendered in the final output types (v1, v2, v3).

learning-agenda