The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from external sources which presents an indirect prompt injection surface.\n
Ingestion points: The workflow in reference/priorities.md uses gmail_search, outlook_search, and meeting_lookup to retrieve user data.\n
Boundary markers: The instructions do not define specific delimiters or "ignore embedded instructions" prompts when processing retrieved content.\n
Capability inventory: No subprocess calls, file writing, or external network operations are present in the skill's instruction set or referenced files.\n
Sanitization: There is no evidence of sanitization or filtering of the retrieved data to prevent prompt injection.

using-glean-productivity