The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by reading from and writing to local context files.
Ingestion points: The skill reads .agents/em-context.md and .agents/reports/[name].md to gather manager and employee context.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the ingestion logic.
Capability inventory: The skill possesses the ability to read and write files within the .agents/ directory.
Sanitization: There is no evidence of sanitization or filtering for content read from these files.
[EXTERNAL_DOWNLOADS]: The skill contains links to external articles for further reading.
Evidence: Links in references/sources.md point to newsletter.manager.dev.
Context: These resources belong to the vendor's official domain and are documented neutrally as intended educational material.

written-communication